updated benchs
This commit is contained in:
@@ -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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
||||
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 431.29 ± 3.17 |
|
||||
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 25.10 ± 0.01 |
|
||||
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 439.13 ± 4.42 |
|
||||
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 25.54 ± 0.00 |
|
||||
|
||||
build: f1fbffb5 (6486)
|
||||
build: a3cb0474 (6735)
|
||||
|
||||
Reference in New Issue
Block a user