[MoE Refactor] Add Temporary Integration Tests - H100/B200 (#31759)

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml

+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 --tensor-parallel-size 2"
+env:
+  VLLM_USE_FLASHINFER_MOE_FP4: "1"
+  VLLM_FLASHINFER_MOE_BACKEND: "latency"

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-marlin.yaml

+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 --tensor-parallel-size 2"
+env:
+  VLLM_TEST_FORCE_FP8_MARLIN: "1"

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml

+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 --tensor-parallel-size 2"

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

+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"

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml

+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 --tensor-parallel-size 2"
+env:
+  VLLM_USE_FLASHINFER_MOE_FP4: "1"
+  VLLM_FLASHINFER_MOE_BACKEND: "throughput"

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml

+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 --tensor-parallel-size 2"
+env:
+  VLLM_USE_FLASHINFER_MOE_FP4: "1"
+  VLLM_FLASHINFER_MOE_BACKEND: "latency"

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml

+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 --tensor-parallel-size 2"
+env:
+  VLLM_TEST_FORCE_FP8_MARLIN: "1"

tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml

+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 --tensor-parallel-size 2"

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

+Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml  
+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

tests/evals/gsm8k/configs/moe-refactor/config-h100.txt

+Mixtral-8x7B-Fp8-AutoFp8-triton.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-marlin.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-triton.yaml
+Qwen3-30B-A3B-Fp8-CT-Block-deepgemm.yaml
+Qwen3-30B-A3B-Fp8-CT-Block-marlin.yaml
+Qwen3-30B-A3B-Fp8-CT-Block-vllm-cutlass.yaml
+Qwen3-30B-A3B-Fp8-CT-Channel-marlin.yaml
+Qwen3-30B-A3B-Fp8-CT-Channel-vllm-cutlass.yaml
+Llama-4-Scout-Fp8-ModelOpt-fi-cutlass.yaml
+Llama-4-Scout-Fp8-ModelOpt-marlin.yaml
+Llama-4-Scout-Fp8-ModelOpt-triton.yaml