updated benchs
This commit is contained in:
@@ -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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | pp512 | 583.32 ± 3.38 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | tg128 | 14.86 ± 0.01 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | pp512 | 451.11 ± 2.96 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | tg128 | 16.83 ± 0.01 |
|
||||
|
||||
build: f1fbffb5 (6486)
|
||||
build: a3cb0474 (6735)
|
||||
|
||||
Reference in New Issue
Block a user