Updated benchmarks

README.md

@@ -51,7 +51,6 @@ You can check the containers on DockerHub: https://hub.docker.com/r/kyuz0/amd-st
 | `rocm-6.4.2-rocwmma` | ROCm 6.4.2 (HIP) + ROCWMMA | ROCm with ROCWMMA enabled for improved flash attention on RDNA3+/CDNA. |
 | `rocm-6.4.3`         | ROCm 6.4.3 (HIP) + hipBLASLt*          | Latest stable ROCm. Great for BF16 models. Occasional crashes possible. |
 | `rocm-6.4.3-rocwmma` | ROCm 6.4.3 (HIP) + ROCWMMA + hipBLASLt*  | ROCm with ROCWMMA enabled for improved flash attention on RDNA3+/CDNA. |
-| `rocm-7beta`         | ROCm 7.0 Beta (HIP) + hipBLASLt*      | Latest ROCm beta. No real gain for Llama.cpp. Same model limits as 6.4.2. |
 | `rocm-7rc`           | ROCm 7.0 RC (HIP) + hipBLASLt*         | Release candidate for ROCm 7.0. Same behavior as beta. |
 | `rocm-7rc-rocwmma`   | ROCm 7.0 RC (HIP) + ROCWMMA + hipBLASLt*       | Release candidate for ROCm 7.0, with hipBLASLt and ROCWMMA for improved flash attention on RDNA3+/CDNA |
 

benchmark/generate_results.json.py

@@ -235,7 +235,7 @@ for path in sorted(glob.glob(os.path.join(RESULTS_DIR, "*.log"))):
 # Meta
 meta = {
     "generated_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
-    "os_kernel": "Fedora 42 — Linux fedora 6.16.0-264.vanilla.fc42.x86_64 (2025-07-28)",
+    "os_kernel": "Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug  2 11:37:34 UTC 2025)",
     "llamacpp_builds": [{"hash": h, "number": n} for (h, n) in sorted(builds)],
     "environments": sorted(envs),
     "notes": "pp512 = prompt processing; tg128 = text generation; t/s = tokens/second",

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_2-rocwmma.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x19cb8050) reason :GPU Hang
+Memory access fault by GPU node-1 (Agent handle: 0x275a2540) on address 0x7f3fb2c08000. Reason: Page not present or supervisor privilege.
 ✖ ! [rocm6_4_2-rocwmma] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_2-rocwmma__fa1.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+HW Exception by GPU node-1 (Agent handle: 0x25d19540) reason :GPU Hang
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+✖ ! [rocm6_4_2-rocwmma] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __fa1 failed (exit 134)
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        139.31 ± 0.13 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         19.97 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_2.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        130.07 ± 0.32 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        131.14 ± 0.28 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         19.48 ± 0.01 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.15 ± 0.01 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_2__fa1.log

@@ -2,5 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x50e2050) reason :GPU Hang
+| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
-✖ ! [rocm6_4_2] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __fa1 failed (exit 134)
+| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        104.12 ± 0.05 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         20.35 ± 0.00 |
+
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3-rocwmma.log

@@ -0,0 +1,15 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+rocBLAS error: No hipBLASLt solution found
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
+
+rocBLAS warning: hipBlasLT failed, falling back to tensile. 
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        126.62 ± 0.10 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         19.95 ± 0.02 |
+
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3-rocwmma__fa1.log

@@ -1,10 +1,10 @@
 ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |        103.63 ± 0.10 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        135.10 ± 0.35 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         20.09 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         20.14 ± 0.01 |
 
-build: cd6983d5 (6119)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3-rocwmma__hblt0.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        129.88 ± 0.57 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        130.99 ± 0.36 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         19.43 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.14 ± 0.01 |
 
-build: cd6983d5 (6119)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3-rocwmma__hblt0__fa1.log

@@ -1,10 +1,10 @@
 ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |        100.80 ± 0.14 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        140.15 ± 0.41 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         20.13 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         20.15 ± 0.01 |
 
-build: 79c1160b (6123)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3.log

@@ -0,0 +1,15 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+rocBLAS error: No hipBLASLt solution found
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
+
+rocBLAS warning: hipBlasLT failed, falling back to tensile. 
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        126.66 ± 0.22 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.14 ± 0.00 |
+
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3__fa1.log

@@ -0,0 +1,10 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        100.20 ± 0.13 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         20.30 ± 0.01 |
+
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3__hblt0.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x2edd2a90) reason :GPU Hang
+HW Exception by GPU node-1 (Agent handle: 0x2624d340) reason :GPU Hang
-✖ ! [rocm6_4_2-rocwmma] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 failed (exit 134)
+✖ ! [rocm6_4_3] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_3__hblt0__fa1.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+Memory access fault by GPU node-1 (Agent handle: 0x37c5d340) on address 0x7f2e3516f000. Reason: Page not present or supervisor privilege.
+✖ ! [rocm6_4_3] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_beta.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        124.50 ± 0.25 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         20.02 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_beta__hblt0.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        130.22 ± 0.35 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.00 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_beta__hblt0__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x1f3f20c0) reason :GPU Hang
-✖ ! [rocm7_beta] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc-rocwmma.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        120.16 ± 0.21 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        117.48 ± 0.53 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         19.96 ± 0.01 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.11 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc-rocwmma__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |        133.91 ± 0.57 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        126.27 ± 0.47 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         19.94 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         19.86 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc-rocwmma__hblt0.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        129.49 ± 0.48 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        158.54 ± 0.42 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         19.95 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.11 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc-rocwmma__hblt0__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        138.34 ± 0.27 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        166.11 ± 0.32 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         19.90 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         19.83 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        124.65 ± 0.23 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |         89.60 ± 0.20 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         19.91 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         20.22 ± 0.00 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |        100.90 ± 0.22 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |         64.66 ± 0.16 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         20.15 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         20.35 ± 0.00 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc__hblt0.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+HW Exception by GPU node-1 (Agent handle: 0x1d380ea0) reason :GPU Hang
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+✖ ! [rocm7_rc] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __hblt0 failed (exit 134)
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        129.49 ± 0.14 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         19.88 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7_rc__hblt0__fa1.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+Memory access fault by GPU node-1 (Agent handle: 0x4a0fea0) on address 0x7f3bf796f000. Reason: Page not present or supervisor privilege.
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+✖ ! [rocm7_rc] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        103.73 ± 0.14 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         20.07 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__vulkan_amdvlk.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |    0 |           pp512 |        201.03 ± 0.31 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |    0 |           pp512 |        197.95 ± 0.29 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |    0 |           tg128 |         22.82 ± 0.00 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |    0 |           tg128 |         23.24 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__vulkan_amdvlk__fa1.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           pp512 |        201.89 ± 0.37 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           pp512 |        199.40 ± 0.35 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           tg128 |         22.85 ± 0.01 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           tg128 |         23.26 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__vulkan_radv.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |    0 |           pp512 |        128.01 ± 0.31 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |    0 |           pp512 |        126.28 ± 0.17 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |    0 |           tg128 |         22.92 ± 0.01 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |    0 |           tg128 |         23.33 ± 0.01 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__vulkan_radv__fa1.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           pp512 |        132.56 ± 0.31 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           pp512 |        131.64 ± 0.32 |
-| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           tg128 |         23.31 ± 0.01 |
+| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           tg128 |         23.88 ± 0.01 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_2-rocwmma.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+HW Exception by GPU node-1 (Agent handle: 0x3e28b540) reason :GPU Hang
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+✖ ! [rocm6_4_2-rocwmma] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 failed (exit 134)
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        124.75 ± 0.42 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.43 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_2-rocwmma__fa1.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x2d9b050) reason :GPU Hang
+Memory access fault by GPU node-1 (Agent handle: 0x2bdf8540) on address 0x7f5f95e35000. Reason: Page not present or supervisor privilege.
 ✖ ! [rocm6_4_2-rocwmma] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_2.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+HW Exception by GPU node-1 (Agent handle: 0x3ff2d540) reason :GPU Hang
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+✖ ! [rocm6_4_2] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 failed (exit 134)
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        124.94 ± 0.42 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         15.35 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_2__fa1.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+HW Exception by GPU node-1 (Agent handle: 0x3bb3540) reason :GPU Hang
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+✖ ! [rocm6_4_2] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __fa1 failed (exit 134)
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |        100.41 ± 0.16 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         15.53 ± 0.01 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3-rocwmma.log

@@ -2,9 +2,14 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+rocBLAS error: No hipBLASLt solution found
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
+
+rocBLAS warning: hipBlasLT failed, falling back to tensile. 
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        113.62 ± 0.21 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        121.82 ± 0.35 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         15.47 ± 0.04 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.59 ± 0.00 |
 
-build: cd6983d5 (6119)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3-rocwmma__fa1.log

@@ -1,10 +1,10 @@
 ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |         90.24 ± 0.13 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        126.60 ± 0.30 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         15.55 ± 0.04 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         15.62 ± 0.04 |
 
-build: 79c1160b (6123)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3-rocwmma__hblt0.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+Memory access fault by GPU node-1 (Agent handle: 0x26e36340) on address 0x7fcef3635000. Reason: Page not present or supervisor privilege.
+✖ ! [rocm6_4_3-rocwmma] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3-rocwmma__hblt0__fa1.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+HW Exception by GPU node-1 (Agent handle: 0x35263340) reason :GPU Hang
+✖ ! [rocm6_4_3-rocwmma] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0__fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3.log

@@ -2,9 +2,14 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+rocBLAS error: No hipBLASLt solution found
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
+
+rocBLAS warning: hipBlasLT failed, falling back to tensile. 
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        124.82 ± 0.18 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        117.95 ± 0.30 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         15.35 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.65 ± 0.01 |
 
-build: cd6983d5 (6119)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3__fa1.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-Memory access fault by GPU node-1 (Agent handle: 0x1527fa90) on address 0x7f55d5f6f000. Reason: Page not present or supervisor privilege.
+Memory access fault by GPU node-1 (Agent handle: 0x28aa3340) on address 0x7fb93761b000. Reason: Page not present or supervisor privilege.
-✖ ! [rocm6_4_2] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __fa1 failed (exit 134)
+✖ ! [rocm6_4_3] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3__hblt0.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x3e596050) reason :GPU Hang
+HW Exception by GPU node-1 (Agent handle: 0x14d05340) reason :GPU Hang
-✖ ! [rocm6_4_2-rocwmma] llama3.3-70.6B-Q4_K_M __fa1 failed (exit 134)
+✖ ! [rocm6_4_3] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_3__hblt0__fa1.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x2dab2050) reason :GPU Hang
+HW Exception by GPU node-1 (Agent handle: 0x265e8340) reason :GPU Hang
-✖ ! [rocm6_4_2] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 failed (exit 134)
+✖ ! [rocm6_4_3] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0__fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_beta.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        118.61 ± 0.54 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         15.51 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_beta__hblt0.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        123.75 ± 0.39 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.48 ± 0.01 |
-
-build: 79c1160b (6123)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_beta__hblt0__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-Memory access fault by GPU node-1 (Agent handle: 0x36bce0c0) on address 0x7f6ee1f6f000. Reason: Page not present or supervisor privilege.
-✖ ! [rocm7_beta] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0__fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc-rocwmma.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        118.92 ± 0.39 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |         69.19 ± 0.20 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         15.47 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.64 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc-rocwmma__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |        127.14 ± 0.27 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        114.61 ± 0.20 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         15.47 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         15.51 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc-rocwmma__hblt0.log

@@ -2,4 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc-rocwmma] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0 failed (exit 134)
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        120.88 ± 0.92 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.61 ± 0.09 |
+
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc-rocwmma__hblt0__fa1.log

@@ -2,4 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc-rocwmma] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0__fa1 failed (exit 134)
+| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |        150.07 ± 0.56 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         15.52 ± 0.00 |
+
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           pp512 |        118.52 ± 0.35 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |         69.52 ± 0.17 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |    0 |           tg128 |         15.52 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.63 ± 0.00 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           pp512 |         97.36 ± 0.07 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           pp512 |         74.02 ± 0.13 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       | 999 |  1 |    0 |           tg128 |         15.57 ± 0.02 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |  1 |    0 |           tg128 |         15.73 ± 0.00 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc__hblt0.log

@@ -2,4 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0 failed (exit 134)
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           pp512 |        142.67 ± 0.75 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | ROCm       |  99 |    0 |           tg128 |         15.68 ± 0.00 |
+
+build: de219279 (6181)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7_rc__hblt0__fa1.log

@@ -2,4 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+Memory access fault by GPU node-1 (Agent handle: 0x1c536ea0) on address 0x7f623b57e000. Reason: Page not present or supervisor privilege.
 ✖ ! [rocm7_rc] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 __hblt0__fa1 failed (exit 134)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__vulkan_amdvlk.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |    0 |           pp512 |        223.59 ± 0.50 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |    0 |           pp512 |        219.81 ± 0.70 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |    0 |           tg128 |         16.51 ± 0.01 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |    0 |           tg128 |         16.80 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__vulkan_amdvlk__fa1.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           pp512 |        225.75 ± 0.69 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           pp512 |        222.20 ± 0.63 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           tg128 |         16.53 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           tg128 |         16.82 ± 0.01 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__vulkan_radv.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |    0 |           pp512 |        127.35 ± 0.43 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |    0 |           pp512 |        126.55 ± 0.40 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |    0 |           tg128 |         16.80 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |    0 |           tg128 |         17.07 ± 0.01 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__vulkan_radv__fa1.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           pp512 |        131.91 ± 0.42 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           pp512 |        131.25 ± 0.50 |
-| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     | 999 |  1 |    0 |           tg128 |         17.02 ± 0.00 |
+| glm4moe 106B.A12B Q6_K         |  94.57 GiB |   110.47 B | Vulkan     |  99 |  1 |    0 |           tg128 |         17.31 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm6_4_2__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-Memory access fault by GPU node-1 (Agent handle: 0xae0b050) on address 0x7f17943a9000. Reason: Page not present or supervisor privilege.
-✖ ! [rocm6_4_2] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_beta.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |    0 |           pp512 |        108.88 ± 0.21 |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |    0 |           tg128 |          2.65 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_beta__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-Memory access fault by GPU node-1 (Agent handle: 0x1f7690e0) on address 0x7f6093d6f000. Reason: Page not present or supervisor privilege.
-✖ ! [rocm7_beta] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_beta__hblt0.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x2ae290c0) reason :GPU Hang
-✖ ! [rocm7_beta] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_beta__hblt0__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x19f880e0) reason :GPU Hang
-✖ ! [rocm7_beta] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |    0 |           pp512 |        109.02 ± 0.07 |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |    0 |           tg128 |          2.65 ± 0.00 |
-
-build: 34c9d765 (6122)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma__fa1.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |  1 |    0 |           pp512 |        117.34 ± 0.09 |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |  1 |    0 |           tg128 |          2.65 ± 0.00 |
-
-build: 34c9d765 (6122)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma__hblt0.log

@@ -1,5 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc-rocwmma] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma__hblt0__fa1.log

@@ -1,5 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc-rocwmma] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |    0 |           pp512 |        109.17 ± 0.12 |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | ROCm       | 999 |    0 |           tg128 |          2.65 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc__fa1.log

@@ -1,5 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc__hblt0.log

@@ -1,5 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__rocm7_rc__hblt0__fa1.log

@@ -1,5 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__vulkan_amdvlk.log

@@ -1,8 +0,0 @@
-ggml_vulkan: Found 1 Vulkan devices:
-ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-ggml_vulkan: Device memory allocation of size 2491416576 failed.
-ggml_vulkan: Requested buffer size exceeds device memory allocation limit: ErrorOutOfDeviceMemory
-main: error: failed to load model '/mnt/models/kimi-dev-72B-Q8_K_XL/UD-Q8_K_XL/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002.gguf'
-✖ ! [vulkan_amdvlk] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 failed (exit 1)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__vulkan_amdvlk__fa1.log

@@ -1,8 +0,0 @@
-ggml_vulkan: Found 1 Vulkan devices:
-ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-ggml_vulkan: Device memory allocation of size 2491416576 failed.
-ggml_vulkan: Requested buffer size exceeds device memory allocation limit: ErrorOutOfDeviceMemory
-main: error: failed to load model '/mnt/models/kimi-dev-72B-Q8_K_XL/UD-Q8_K_XL/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002.gguf'
-✖ ! [vulkan_amdvlk] Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 1)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__vulkan_radv.log

@@ -1,8 +0,0 @@
-ggml_vulkan: Found 1 Vulkan devices:
-ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | Vulkan     | 999 |    0 |           pp512 |         78.54 ± 0.14 |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | Vulkan     | 999 |    0 |           tg128 |          2.67 ± 0.00 |
-
-build: 34c9d765 (6122)

benchmark/results/Kimi-Dev-72B-UD-Q8_K_XL-00001-of-00002__vulkan_radv__fa1.log

@@ -1,8 +0,0 @@
-ggml_vulkan: Found 1 Vulkan devices:
-ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | Vulkan     | 999 |  1 |    0 |           pp512 |         81.12 ± 0.08 |
-| qwen2 70B Q8_0                 |  78.21 GiB |    72.71 B | Vulkan     | 999 |  1 |    0 |           tg128 |          2.67 ± 0.00 |
-
-build: 34c9d765 (6122)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_2-rocwmma.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0xd004050) reason :GPU Hang
+HW Exception by GPU node-1 (Agent handle: 0x33b8a540) reason :GPU Hang
 ✖ ! [rocm6_4_2-rocwmma] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_2-rocwmma__fa1.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x1fdc2050) reason :GPU Hang
+HW Exception by GPU node-1 (Agent handle: 0x20e35540) reason :GPU Hang
 ✖ ! [rocm6_4_2-rocwmma] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_2.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+HW Exception by GPU node-1 (Agent handle: 0x1b1ea540) reason :GPU Hang
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+✖ ! [rocm6_4_2] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 failed (exit 134)
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           pp512 |         33.28 ± 0.05 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           tg128 |          2.73 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_2__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           pp512 |         30.88 ± 0.02 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           pp512 |         16.16 ± 0.02 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           tg128 |          2.73 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           tg128 |          2.78 ± 0.00 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3-rocwmma.log

@@ -2,9 +2,14 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+hipBLASLt error: Heuristic Fetch Failed!
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
+
+rocBLAS warning: hipBlasLT failed, falling back to tensile. 
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           pp512 |         33.32 ± 0.04 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           pp512 |         98.02 ± 0.18 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           tg128 |          2.73 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           tg128 |          2.77 ± 0.00 |
 
-build: cd6983d5 (6119)
+build: 1fe00296 (6182)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3-rocwmma__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           pp512 |         31.28 ± 0.02 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           pp512 |        101.83 ± 0.11 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           tg128 |          2.74 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           tg128 |          2.77 ± 0.00 |
 
-build: cd6983d5 (6119)
+build: 1fe00296 (6182)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3-rocwmma__hblt0.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+HW Exception by GPU node-1 (Agent handle: 0x21da1340) reason :GPU Hang
+✖ ! [rocm6_4_3-rocwmma] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3-rocwmma__hblt0__fa1.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+HW Exception by GPU node-1 (Agent handle: 0x15ac2340) reason :GPU Hang
+✖ ! [rocm6_4_3-rocwmma] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3.log

@@ -0,0 +1,15 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+hipBLASLt error: Heuristic Fetch Failed!
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
+
+rocBLAS warning: hipBlasLT failed, falling back to tensile. 
+This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           pp512 |         97.13 ± 0.17 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           tg128 |          2.78 ± 0.00 |
+
+build: 1fe00296 (6182)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| llama 70B Q4_K - Medium        |  39.59 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           pp512 |         31.69 ± 0.04 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           pp512 |         80.42 ± 0.08 |
-| llama 70B Q4_K - Medium        |  39.59 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           tg128 |          4.62 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           tg128 |          2.78 ± 0.00 |
 
-build: 79c1160b (6123)
+build: 1fe00296 (6182)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3__hblt0.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+HW Exception by GPU node-1 (Agent handle: 0x2c1e5340) reason :GPU Hang
+✖ ! [rocm6_4_3] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_3__hblt0__fa1.log

@@ -0,0 +1,6 @@
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 ROCm devices:
+  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
+Memory access fault by GPU node-1 (Agent handle: 0x3e536340) on address 0x7f9182f6f000. Reason: Page not present or supervisor privilege.
+✖ ! [rocm6_4_3] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_beta.log

@@ -1,10 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
-| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           pp512 |         95.65 ± 0.23 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           tg128 |          2.74 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_beta__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-Memory access fault by GPU node-1 (Agent handle: 0x2e9460f0) on address 0x7f23cf58a000. Reason: Page not present or supervisor privilege.
-✖ ! [rocm7_beta] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_beta__hblt0.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-HW Exception by GPU node-1 (Agent handle: 0x2c3170e0) reason :GPU Hang
-✖ ! [rocm7_beta] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_beta__hblt0__fa1.log

@@ -1,6 +0,0 @@
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
-ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
-ggml_cuda_init: found 1 ROCm devices:
-  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-Memory access fault by GPU node-1 (Agent handle: 0xe3f70e0) on address 0x7f4e23b6f000. Reason: Page not present or supervisor privilege.
-✖ ! [rocm7_beta] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           pp512 |         95.63 ± 0.19 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           pp512 |         97.31 ± 0.20 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           tg128 |          2.73 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           tg128 |          2.78 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma__fa1.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           pp512 |        103.15 ± 0.13 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           pp512 |        100.85 ± 0.13 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |  1 |    0 |           tg128 |          2.73 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           tg128 |          2.77 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma__hblt0.log

@@ -2,4 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc-rocwmma] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           pp512 |         93.00 ± 0.22 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           tg128 |          2.78 ± 0.00 |
+
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc-rocwmma__hblt0__fa1.log

@@ -2,4 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc-rocwmma] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)
+| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           pp512 |         97.88 ± 0.09 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           tg128 |          2.77 ± 0.00 |
+
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc.log

@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           pp512 |         95.15 ± 0.14 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           pp512 |         99.41 ± 0.36 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       | 999 |    0 |           tg128 |          2.74 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           tg128 |          2.77 ± 0.00 |
 
-build: 79c1160b (6123)
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc__fa1.log

@@ -2,5 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-:0:rocdevice.cpp            :3594: 448132897452 us:  Callback: Queue 0x7f7ecc400000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
+Memory access fault by GPU node-1 (Agent handle: 0x1f66bec0) on address 0x7f3e84b6f000. Reason: Page not present or supervisor privilege.
 ✖ ! [rocm7_rc] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __fa1 failed (exit 134)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc__hblt0.log

@@ -2,4 +2,9 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-✖ ! [rocm7_rc] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0 failed (exit 134)
+| model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
+| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           pp512 |         94.06 ± 0.09 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |    0 |           tg128 |          2.78 ± 0.00 |
+
+build: de219279 (6181)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_rc__hblt0__fa1.log

@@ -2,9 +2,5 @@ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
 ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 ggml_cuda_init: found 1 ROCm devices:
   Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
-| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
+Memory access fault by GPU node-1 (Agent handle: 0xac09ec0) on address 0x7f283f56f000. Reason: Page not present or supervisor privilege.
-| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
+✖ ! [rocm7_rc] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 __hblt0__fa1 failed (exit 134)
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           pp512 |         30.04 ± 0.04 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |  1 |    0 |           tg128 |          2.74 ± 0.00 |
-
-build: 79c1160b (6123)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__vulkan_amdvlk.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     | 999 |    0 |           pp512 |         98.20 ± 0.18 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     |  99 |    0 |           pp512 |         98.03 ± 0.24 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     | 999 |    0 |           tg128 |          2.75 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     |  99 |    0 |           tg128 |          2.78 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__vulkan_amdvlk__fa1.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     | 999 |  1 |    0 |           pp512 |         99.14 ± 0.35 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     |  99 |  1 |    0 |           pp512 |         99.12 ± 0.25 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     | 999 |  1 |    0 |           tg128 |          2.74 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     |  99 |  1 |    0 |           tg128 |          2.77 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)

benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__vulkan_radv.log

@@ -2,7 +2,7 @@ ggml_vulkan: Found 1 Vulkan devices:
 ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
 | model                          |       size |     params | backend    | ngl | mmap |            test |                  t/s |
 | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     | 999 |    0 |           pp512 |         79.91 ± 0.16 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     |  99 |    0 |           pp512 |         75.59 ± 0.28 |
-| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     | 999 |    0 |           tg128 |          2.75 ± 0.00 |
+| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | Vulkan     |  99 |    0 |           tg128 |          2.78 ± 0.00 |
 
-build: 34c9d765 (6122)
+build: 1fe00296 (6182)