Added link to YouTube video and updated benchmarks
This commit is contained in:
@@ -0,0 +1,108 @@
|
||||
#!/usr/bin/env python3
|
||||
import re, glob, os, argparse
|
||||
|
||||
PP_RE = re.compile(r"\|[^|]*\|[^|]*\|[^|]*\|[^|]*\|[^|]*\|\s*pp512\s*\|\s*([\d.]+)\s*±\s*([\d.]+)")
|
||||
TG_RE = re.compile(r"\|[^|]*\|[^|]*\|[^|]*\|[^|]*\|[^|]*\|\s*tg128\s*\|\s*([\d.]+)\s*±\s*([\d.]+)")
|
||||
LOAD_ERR = re.compile(r"failed to load model|Device memory allocation.*failed", re.IGNORECASE)
|
||||
HANG_ERR = re.compile(r"GPU Hang|HW Exception", re.IGNORECASE)
|
||||
GEN_ERR = re.compile(r"error:|exit \d+", re.IGNORECASE)
|
||||
|
||||
ENV_ORDER = ["vulkan_amdvlk","vulkan_radv","rocm6_4_2","rocm7_beta","rocm7_rc"]
|
||||
COL_NAMES = {
|
||||
"vulkan_amdvlk":"Vulkan (AMDVLK)",
|
||||
"vulkan_radv":"Vulkan (RADV)",
|
||||
"rocm6_4_2":"ROCm 6.4.2",
|
||||
"rocm7_beta":"ROCm 7.0 Beta",
|
||||
"rocm7_rc":"ROCm 7.0 RC",
|
||||
}
|
||||
WINNER = {
|
||||
"vulkan_amdvlk":"AMDVLK",
|
||||
"vulkan_radv":"RADV",
|
||||
"rocm6_4_2":"ROCm6.4.2",
|
||||
"rocm7_beta":"ROCm7 Beta",
|
||||
"rocm7_rc":"ROCm7 RC",
|
||||
}
|
||||
|
||||
DEFAULT_MODELS = [
|
||||
("Gemma3 12B Q8_0", "gemma-3-12b-it-UD-Q8_K_XL"),
|
||||
("Gemma3 27B BF16", "gemma-3-27b-it-BF16"),
|
||||
("Llama-4-Scout 17B Q8_0", "Llama-4-Scout-17B-16E-Instruct-Q8_0"),
|
||||
("Llama-4-Scout 17B Q4_K XL", "Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL"),
|
||||
("Qwen3 30B BF16", "Qwen3-30B-A3B-BF16"),
|
||||
("Qwen3-235B Q3_K XL", "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL"),
|
||||
("GLM-4.5-Air-UD-Q4_K_XL", "GLM-4.5-Air-UD-Q4_K_XL"),
|
||||
("GLM-4.5-Air-UD-Q6_K_XL", "GLM-4.5-Air-UD-Q6_K_XL"),
|
||||
("gpt-oss-120b-mxfp4", "gpt-oss-120b-mxfp4"),
|
||||
("gpt-oss-20b-mxfp4", "gpt-oss-20b-mxfp4"),
|
||||
]
|
||||
|
||||
CLEAN = lambda s: re.sub(r"-000\d+-of-000\d+", "", s)
|
||||
|
||||
def parse_logs():
|
||||
data = {}
|
||||
for p in glob.glob(os.path.join("results","*.log")):
|
||||
base = os.path.basename(p)[:-4]
|
||||
if "__" not in base:
|
||||
continue
|
||||
model_raw, env = base.split("__", 1)
|
||||
key = CLEAN(model_raw)
|
||||
t = open(p, errors="ignore").read()
|
||||
pp = PP_RE.search(t)
|
||||
tg = TG_RE.search(t)
|
||||
et = None
|
||||
if LOAD_ERR.search(t): et = "load"
|
||||
elif HANG_ERR.search(t): et = "hang"
|
||||
elif GEN_ERR.search(t) and not (pp and tg): et = "runtime"
|
||||
data.setdefault(key, {"pp512": {}, "tg128": {}})
|
||||
data[key]["pp512"][env] = {"mean": float(pp.group(1)) if (pp and et is None) else None,
|
||||
"error": et is not None, "etype": et}
|
||||
data[key]["tg128"][env] = {"mean": float(tg.group(1)) if (tg and et is None) else None,
|
||||
"error": et is not None, "etype": et}
|
||||
return data
|
||||
|
||||
def best(env_data):
|
||||
vals = {e:d["mean"] for e,d in env_data.items() if (not d["error"]) and d["mean"] is not None}
|
||||
return max(vals, key=vals.get) if vals else None
|
||||
|
||||
def cell(pp, tg):
|
||||
if (pp is None) or (tg is None):
|
||||
return "—"
|
||||
if pp["error"] or tg["error"]:
|
||||
m = pp["etype"] or tg["etype"] or "runtime"
|
||||
return {"load":"⚠️ Load Error","hang":"⚠️ GPU Hang","runtime":"⚠️ Runtime Error"}.get(m, "⚠️ Error")
|
||||
return f"{int(round(pp['mean']))} pp / {tg['mean']:.1f} tg"
|
||||
|
||||
def find_key(keys, prefix):
|
||||
for k in keys:
|
||||
if k.startswith(prefix):
|
||||
return k
|
||||
return None
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("models", nargs="*", help="Optional model prefixes to include")
|
||||
args = ap.parse_args()
|
||||
data = parse_logs()
|
||||
want = [(m,m) for m in args.models] if args.models else DEFAULT_MODELS
|
||||
|
||||
header = ["Model"] + [COL_NAMES[e] for e in ENV_ORDER] + ["🏆 Best PP","🏆 Best TG"]
|
||||
print("| " + " | ".join(header) + " |")
|
||||
print("|" + "|".join(["---"]*len(header)) + "|")
|
||||
|
||||
for disp, patt in want:
|
||||
key = find_key(data.keys(), patt)
|
||||
row = [f"**{disp}**"]
|
||||
if not key:
|
||||
row += ["—"]*len(ENV_ORDER) + ["—","—"]
|
||||
print("| " + " | ".join(row) + " |")
|
||||
continue
|
||||
ppd, tgd = data[key]["pp512"], data[key]["tg128"]
|
||||
for env in ENV_ORDER:
|
||||
row.append(cell(ppd.get(env), tgd.get(env)))
|
||||
bpp, btg = best(ppd), best(tgd)
|
||||
row.append(f"🏆 **{WINNER[bpp]}**" if bpp else "—")
|
||||
row.append(f"🏆 **{WINNER[btg]}**" if btg else "—")
|
||||
print("| " + " | ".join(row) + " |")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -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: 0x7f5e570) on address 0x7f3192c0f000. Reason: Page not present or supervisor privilege.
|
||||
✖ ! [rocm6_4_2] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 failed (exit 134)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
HW Exception by GPU node-1 (Agent handle: 0x16bd82e0) reason :GPU Hang
|
||||
✖ ! [rocm7_beta] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 failed (exit 134)
|
||||
@@ -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: 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 | 129.20 ± 0.38 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 19.61 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 | 99 | 0 | pp512 | 199.54 ± 0.38 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | Vulkan | 99 | 0 | tg128 | 22.75 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 | 99 | 0 | pp512 | 128.00 ± 0.23 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | Vulkan | 99 | 0 | tg128 | 22.88 ± 0.02 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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 | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 124.86 ± 0.54 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 15.27 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
HW Exception by GPU node-1 (Agent handle: 0x2a5da2e0) reason :GPU Hang
|
||||
✖ ! [rocm7_beta] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 failed (exit 134)
|
||||
@@ -0,0 +1,5 @@
|
||||
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
|
||||
✖ ! [rocm7_rc] GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003 failed (exit 134)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 | 99 | 0 | pp512 | 221.02 ± 0.58 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | Vulkan | 99 | 0 | tg128 | 16.47 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 | 99 | 0 | pp512 | 126.86 ± 0.40 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | Vulkan | 99 | 0 | tg128 | 16.76 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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 | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 729.02 ± 0.82 |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 76.04 ± 0.03 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 729.93 ± 1.29 |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 76.52 ± 0.03 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 728.63 ± 1.23 |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 75.59 ± 0.03 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | Vulkan | 99 | 0 | pp512 | 1616.55 ± 4.61 |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | Vulkan | 99 | 0 | tg128 | 83.89 ± 0.22 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | Vulkan | 99 | 0 | pp512 | 1520.07 ± 5.39 |
|
||||
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | Vulkan | 99 | 0 | tg128 | 85.93 ± 0.09 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: 0x394d3570) reason :GPU Hang
|
||||
✖ ! [rocm6_4_2] gpt-oss-120b-F16 failed (exit 134)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 357.68 ± 1.49 |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 33.70 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 355.47 ± 0.55 |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 33.65 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | Vulkan | 99 | 0 | pp512 | 449.22 ± 1.12 |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | Vulkan | 99 | 0 | tg128 | 33.49 ± 0.05 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | Vulkan | 99 | 0 | pp512 | 230.32 ± 0.72 |
|
||||
| gpt-oss ?B F16 | 60.87 GiB | 116.83 B | Vulkan | 99 | 0 | tg128 | 33.06 ± 0.02 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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 | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 352.53 ± 1.06 |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 43.56 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
HW Exception by GPU node-1 (Agent handle: 0x299852d0) reason :GPU Hang
|
||||
✖ ! [rocm7_beta] gpt-oss-120b-mxfp4-00001-of-00003 failed (exit 134)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 351.08 ± 0.86 |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 44.63 ± 0.03 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | Vulkan | 99 | 0 | pp512 | 485.98 ± 2.23 |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | Vulkan | 99 | 0 | tg128 | 48.09 ± 0.04 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | Vulkan | 99 | 0 | pp512 | 239.16 ± 1.26 |
|
||||
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | Vulkan | 99 | 0 | tg128 | 48.93 ± 0.06 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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 | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 323.64 ± 4.29 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 26.64 ± 0.06 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 324.15 ± 3.76 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 26.90 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 324.27 ± 5.39 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 26.86 ± 0.00 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 0 | pp512 | 369.86 ± 1.57 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 0 | tg128 | 8.59 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 0 | pp512 | 318.82 ± 1.63 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 0 | tg128 | 7.77 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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 | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 580.67 ± 2.03 |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 64.26 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 584.04 ± 2.48 |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 64.37 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 584.15 ± 2.11 |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 64.38 ± 0.01 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 0 | pp512 | 1206.08 ± 8.80 |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 0 | tg128 | 68.90 ± 0.18 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
@@ -0,0 +1,8 @@
|
||||
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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 0 | pp512 | 646.77 ± 4.63 |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 0 | tg128 | 69.82 ± 0.03 |
|
||||
|
||||
build: 0d883154 (6101)
|
||||
Reference in New Issue
Block a user