[Quantization][CI] add humming lm-eval test (#43752)

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Jinzhen Lin
2026-06-22 11:23:55 -07:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 3e6529cc0e
commit e4b3da3feb
9 changed files with 91 additions and 2 deletions
@@ -0,0 +1,12 @@
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
--tensor-parallel-size 1
--quantization humming
--kernel-config.enable_flashinfer_autotune=False
env:
VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,10 @@
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
--tensor-parallel-size 1
--quantization humming
--kernel-config.enable_flashinfer_autotune=False
@@ -0,0 +1,2 @@
gpt-oss-20b-humming-act-fp8.yaml
Qwen3-30B-A3B-MXFP4A16-humming-act-fp8.yaml
@@ -0,0 +1,2 @@
gpt-oss-20b-humming.yaml
Qwen3-30B-A3B-MXFP4A16-humming.yaml
@@ -0,0 +1,11 @@
model_name: "openai/gpt-oss-20b"
accuracy_threshold: 0.30
num_questions: 1319
num_fewshot: 5
server_args: >-
--enforce-eager
--max-model-len 8192
--tensor-parallel-size 1
--moe-backend humming
env:
VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,9 @@
model_name: "openai/gpt-oss-20b"
accuracy_threshold: 0.30
num_questions: 1319
num_fewshot: 5
server_args: >-
--enforce-eager
--max-model-len 8192
--tensor-parallel-size 1
--moe-backend humming