Remove wrongly added e2e test (#54099)
This commit is contained in:
@@ -1,11 +0,0 @@
|
|||||||
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}'
|
|
||||||
@@ -1,6 +1,5 @@
|
|||||||
gpt-oss-20b-humming-act-fp8.yaml
|
gpt-oss-20b-humming-act-fp8.yaml
|
||||||
Qwen3-30B-A3B-MXFP4A16-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
|
Qwen2-1.5B-Instruct-FP8W8-humming-act-fp8.yaml
|
||||||
Qwen3-0.6B-MXFP8-humming-act-fp8.yaml
|
Qwen3-0.6B-MXFP8-humming-act-fp8.yaml
|
||||||
Qwen3-30B-A3B-Fp8-v1-humming-act-fp8.yaml
|
Qwen3-30B-A3B-Fp8-v1-humming-act-fp8.yaml
|
||||||
|
|||||||
Reference in New Issue
Block a user