From 254db42ede6beb7d3191f50084594c0ce791ce40 Mon Sep 17 00:00:00 2001 From: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Date: Mon, 26 Jan 2026 00:23:54 -0500 Subject: [PATCH] [Tests] Remove Duplicates (#33032) Signed-off-by: Robert Shaw Co-authored-by: Robert Shaw --- .../Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml | 8 -------- .../Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml | 8 -------- tests/evals/gsm8k/configs/moe-refactor/config-b200.txt | 2 -- 3 files changed, 18 deletions(-) delete mode 100644 tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml delete mode 100644 tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml diff --git a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml deleted file mode 100644 index 53fd62bac..000000000 --- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass-dp-ep.yaml +++ /dev/null @@ -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" diff --git a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml deleted file mode 100644 index 44f8700e4..000000000 --- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass-dp-ep.yaml +++ /dev/null @@ -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" diff --git a/tests/evals/gsm8k/configs/moe-refactor/config-b200.txt b/tests/evals/gsm8k/configs/moe-refactor/config-b200.txt index 95e91fb08..a7c55a6ef 100644 --- a/tests/evals/gsm8k/configs/moe-refactor/config-b200.txt +++ b/tests/evals/gsm8k/configs/moe-refactor/config-b200.txt @@ -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