[Quantization][Humming] Support MXFP4 weight + block-FP8 activation for MoE (#51332)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com> Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Signed-off-by: Elvir Crnčević <elvircrn@gmail.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
Tyler Michael Smith
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
9c8e90eb26
commit
ca29cd48ba
@@ -0,0 +1,11 @@
|
||||
model_name: "nm-testing/Qwen3-30B-A3B-MXFP4A16"
|
||||
accuracy_threshold: 0.86
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: >-
|
||||
--enforce-eager
|
||||
--max-model-len 8192
|
||||
--quantization humming
|
||||
--linear-backend humming
|
||||
env:
|
||||
VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3","group_size":128}'
|
||||
@@ -1,5 +1,6 @@
|
||||
gpt-oss-20b-humming-act-fp8.yaml
|
||||
Qwen3-30B-A3B-MXFP4A16-humming-act-fp8.yaml
|
||||
Qwen3-30B-A3B-MXFP4A16-humming-act-fp8-block.yaml
|
||||
Qwen2-1.5B-Instruct-FP8W8-humming-act-fp8.yaml
|
||||
Qwen3-0.6B-MXFP8-humming-act-fp8.yaml
|
||||
Qwen3-30B-A3B-Fp8-v1-humming-act-fp8.yaml
|
||||
|
||||
Reference in New Issue
Block a user