[ROCm][Quark][6/N] Use MXFP4 linear kernel abstraction for aiter backend (#49348)
Signed-off-by: Felix Marty <Felix.Marty@amd.com> Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
co-authored by
Andreas Karatzas
parent
73af7a362a
commit
7aea73d83d
@@ -0,0 +1,5 @@
|
||||
model_name: "amd-quark/Qwen3-1.7B-MXFP4"
|
||||
accuracy_threshold: 0.27
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: "--enforce-eager --max-model-len 4096"
|
||||
Reference in New Issue
Block a user