julian/amd-strix-halo-toolboxes
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

updated benchmarks

Browse Source
This commit is contained in:
Donato Capitella
2025-12-21 18:49:08 +00:00
parent 9ba6812003
commit 2c8a1e2eef
991 changed files with 23078 additions and 35790 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/llama-2-7b.Q4_0__rocm7.1.1__hblt0__fa1__longctx16384.log
+10
View File
@@ -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 | n_ubatch | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d16384 | 348.73 ± 0.00 |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d16384 | 13.36 ± 0.00 |
build: 2aa45ef9e (7423)