biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Tests] Remove Duplicates (#33032)

Browse Source 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
This commit is contained in:
Robert Shaw
2026-01-26 00:23:54 -05:00
committed by GitHub
parent 105d104576
commit 254db42ede
3 changed files with 0 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml
View File

@@ -1,8 +0,0 @@
model_name: "RedHatAI/Qwen3-30B-A3B-NVFP4"
accuracy_threshold: 0.88
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel"
env:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_FLASHINFER_MOE_BACKEND: "throughput"

8
tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml
View File

@@ -1,8 +0,0 @@
model_name: "nvidia/Qwen3-30B-A3B-NVFP4"
accuracy_threshold: 0.88
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel"
env:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_FLASHINFER_MOE_BACKEND: "throughput"

2
tests/evals/gsm8k/configs/moe-refactor/config-b200.txt
View File

@@ -5,12 +5,10 @@ Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
Qwen3-30B-A3B-NvFp4-CT-marlin.yaml
Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml
Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml
Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml
Llama-4-Scout-BF16-fi-cutlass.yaml
Llama-4-Scout-BF16-triton.yaml
Mixtral-8x7B-BF16-fi-cutlass.yaml