Enabling some B200-specific tests on MI355 (#35253)
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com> Signed-off-by: Alexei-V-Ivanov-AMD <156011006+Alexei-V-Ivanov-AMD@users.noreply.github.com>
This commit is contained in:
@@ -0,0 +1,9 @@
|
||||
model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
|
||||
accuracy_threshold: 0.85
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: >-
|
||||
--max-model-len 4096
|
||||
--tensor-parallel-size 2
|
||||
--enable-expert-parallel
|
||||
--async-scheduling
|
||||
@@ -0,0 +1,5 @@
|
||||
Qwen3-0.6B-FP8.yaml
|
||||
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
|
||||
Qwen1.5-MoE-W4A16-CT.yaml
|
||||
DeepSeek-V2-Lite-Instruct-FP8.yaml
|
||||
Qwen3-Next-FP8-EP2_MI355.yaml
|
||||
Reference in New Issue
Block a user