Donato Capitella
13 lines
1.2 KiB
Plaintext
13 lines
1.2 KiB
Plaintext
WARNING: radv is not a conformant Vulkan implementation, testing use only.
|
|
WARNING: radv is not a conformant Vulkan implementation, testing use only.
|
|
ggml_vulkan: Found 3 Vulkan devices:
|
|
ggml_vulkan: 0 = AMD Ryzen 9 9900X3D 12-Core Processor (RADV RAPHAEL_MENDOCINO) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 65536 | int dot: 1 | matrix cores: none
|
|
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
|
|
ggml_vulkan: 2 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
|
|
| model | size | params | backend | ngl | fa | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
|
|
| nemotron_h_moe 31B.A3.5B Q4_K - Medium | 21.26 GiB | 31.58 B | Vulkan | 99 | 1 | pp512 | 1695.40 ± 23.13 |
|
|
| nemotron_h_moe 31B.A3.5B Q4_K - Medium | 21.26 GiB | 31.58 B | Vulkan | 99 | 1 | tg128 | 91.72 ± 0.11 |
|
|
|
|
build: 2aa45ef9e (7423)
|