[Hardware][AMD][CI] Use Triton-based AITER MHA for LM Eval Qwen-3.5 Models Tests (#46691)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
This commit is contained in:
@@ -3,7 +3,6 @@ accuracy_threshold: 0.89
|
||||
tolerance: 0.03
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
startup_max_wait_seconds: 3600
|
||||
server_args: >-
|
||||
--max-model-len 4096
|
||||
--tensor-parallel-size 2
|
||||
@@ -11,3 +10,4 @@ server_args: >-
|
||||
--moe-backend aiter
|
||||
env:
|
||||
VLLM_ROCM_USE_AITER: "1"
|
||||
ENABLE_CK: "0" # Avoid AITER CK-based MHA JIT compilation to save time
|
||||
|
||||
Reference in New Issue
Block a user