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

updted benchmarks

Browse Source
This commit is contained in:
Donato Capitella
2026-03-30 08:37:15 +01:00
parent 614b00af3e
commit a7ace8dba7
595 changed files with 19653 additions and 14511 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/gpt-oss-20b-mxfp4__vulkan_amdvlk__fa1__longctx32768.log
+5 -5
View File
@@ -1,8 +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 | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | pp2048 @ d32768 | 337.80 ± 4.40 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | tg32 @ d32768 | 53.06 ± 0.10 |
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | pp2048 @ d32768 | 364.73 ± 0.33 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | tg32 @ d32768 | 49.99 ± 0.21 |
build: e0c93af2a (7938)
build: 2405d59cb (8577)