[Quant] Support MXFP4 W4A16 for compressed-tensors MoE models (#32285)

Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Dipika Sikka
2026-01-15 07:25:55 -08:00
committed by GitHub
co-authored by Michael Goin
parent 8ebfacaa75
commit 361dfdc9d8
4 changed files with 156 additions and 0 deletions
@@ -0,0 +1,5 @@
model_name: nm-testing/Qwen3-30B-A3B-MXFP4A16
accuracy_threshold: 0.88
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 4096"
@@ -4,3 +4,4 @@ Llama-3-8B-Instruct-nonuniform-CT.yaml
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
Qwen1.5-MoE-W4A16-CT.yaml
DeepSeek-V2-Lite-Instruct-FP8.yaml
Qwen3-30B-A3B-MXFP4A16.yaml