Add vLLM v0.18.1 source tree with KV transfer abort fix

third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:

  vllm/v1/core/sched/scheduler.py:
    Replace fatal assert with graceful skip when KV transfer callback
    arrives for an already-aborted request during PD disaggregated serving.

Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

third_party/vllm/tests/evals/gsm8k/configs/DeepSeek-R1-DP.yaml

@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-R1"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --data-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

third_party/vllm/tests/evals/gsm8k/configs/DeepSeek-R1-TP.yaml

@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-R1"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

third_party/vllm/tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml

@@ -0,0 +1,5 @@
+model_name: "RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8"
+accuracy_threshold: 0.72
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/DeepSeek-V3.2-DP.yaml

@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-V3.2"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --data-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

third_party/vllm/tests/evals/gsm8k/configs/DeepSeek-V3.2-TP.yaml

@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-V3.2"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

third_party/vllm/tests/evals/gsm8k/configs/Llama-3-8B-Instruct-nonuniform-CT.yaml

@@ -0,0 +1,5 @@
+model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test"
+accuracy_threshold: 0.74
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Llama-3.2-1B-Instruct-INT8-CT.yaml

@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8"
+accuracy_threshold: 0.31
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Qwen1.5-MoE-W4A16-CT.yaml

@@ -0,0 +1,5 @@
+model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
+accuracy_threshold: 0.45
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml

@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
+accuracy_threshold: 0.60
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Qwen3-0.6B-FP8.yaml

@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-0.6B-FP8"
+accuracy_threshold: 0.375
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Qwen3-30B-A3B-MXFP4A16.yaml

@@ -0,0 +1,5 @@
+model_name: nm-testing/Qwen3-30B-A3B-MXFP4A16
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Qwen3-30B-A3B-NVFP4.yaml

@@ -0,0 +1,5 @@
+model_name: "nvidia/Qwen3-30B-A3B-FP4"
+accuracy_threshold: 0.89
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"

third_party/vllm/tests/evals/gsm8k/configs/Qwen3-Next-80B-A3B-NVFP4-EP2.yaml

@@ -0,0 +1,11 @@
+model_name: "nm-testing/Qwen3-Next-80B-A3B-Instruct-NVFP4"
+accuracy_threshold: 0.75
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":1}'
+  --moe-backend=flashinfer_trtllm

third_party/vllm/tests/evals/gsm8k/configs/Qwen3-Next-FP8-EP2.yaml

@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --async-scheduling
+  --moe-backend=flashinfer_trtllm

third_party/vllm/tests/evals/gsm8k/configs/Qwen3-Next-FP8-EP2_MI355.yaml

@@ -0,0 +1,9 @@
+model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --async-scheduling

third_party/vllm/tests/evals/gsm8k/configs/Qwen3.5-35B-A3B-DEP2.yaml

@@ -0,0 +1,9 @@
+model_name: "Qwen/Qwen3.5-35B-A3B"
+accuracy_threshold: 0.84
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel

third_party/vllm/tests/evals/gsm8k/configs/Qwen3.5-35B-A3B-FP8-DEP2.yaml

@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3.5-35B-A3B-FP8"
+accuracy_threshold: 0.79
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel
+  --kv-cache-dtype fp8

third_party/vllm/tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2.yaml

@@ -0,0 +1,9 @@
+model_name: "nvidia/Qwen3.5-397B-A17B-NVFP4"
+accuracy_threshold: 0.88
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel

third_party/vllm/tests/evals/gsm8k/configs/models-blackwell.txt

@@ -0,0 +1,7 @@
+Qwen3-0.6B-FP8.yaml
+Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
+Qwen1.5-MoE-W4A16-CT.yaml
+DeepSeek-V2-Lite-Instruct-FP8.yaml
+Qwen3-30B-A3B-NVFP4.yaml
+Qwen3-Next-80B-A3B-NVFP4-EP2.yaml
+Qwen3-Next-FP8-EP2.yaml

third_party/vllm/tests/evals/gsm8k/configs/models-h200.txt

@@ -0,0 +1,4 @@
+DeepSeek-R1-TP.yaml
+DeepSeek-R1-DP.yaml
+DeepSeek-V3.2-TP.yaml
+DeepSeek-V3.2-DP.yaml

third_party/vllm/tests/evals/gsm8k/configs/models-mi355.txt

@@ -0,0 +1,5 @@
+Qwen3-0.6B-FP8.yaml
+Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
+Qwen1.5-MoE-W4A16-CT.yaml
+DeepSeek-V2-Lite-Instruct-FP8.yaml
+Qwen3-Next-FP8-EP2_MI355.yaml

third_party/vllm/tests/evals/gsm8k/configs/models-qwen35-blackwell.txt

@@ -0,0 +1,3 @@
+Qwen3.5-35B-A3B-DEP2.yaml
+Qwen3.5-35B-A3B-FP8-DEP2.yaml
+Qwen3.5-397B-A17B-NVFP4-DEP2.yaml

third_party/vllm/tests/evals/gsm8k/configs/models-small.txt

@@ -0,0 +1,7 @@
+Qwen3-0.6B-FP8.yaml
+Llama-3.2-1B-Instruct-INT8-CT.yaml
+Llama-3-8B-Instruct-nonuniform-CT.yaml
+Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
+Qwen1.5-MoE-W4A16-CT.yaml
+DeepSeek-V2-Lite-Instruct-FP8.yaml
+Qwen3-30B-A3B-MXFP4A16.yaml

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Llama-4-Scout-Fp8-ModelOpt-triton.yaml

@@ -0,0 +1,7 @@
+model_name: "nvidia/Llama-4-Scout-17B-16E-Instruct-FP8"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel --moe-backend=triton"
+env:
+  VLLM_USE_DEEP_GEMM: "0"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-BF16-triton.yaml

@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+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"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm-deepep-ht.yaml

@@ -0,0 +1,8 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+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 --all2all-backend deepep_high_throughput"
+env:
+  VLLM_USE_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm-deepep-ll.yaml

@@ -0,0 +1,8 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+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 --all2all-backend deepep_low_latency --disable-uvicorn-access-log"
+env:
+  VLLM_USE_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm.yaml

@@ -0,0 +1,8 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+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_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-Fp8-CT-Block-deepgemm-deepep-ht.yaml

@@ -0,0 +1,8 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel --all2all-backend deepep_high_throughput"
+env:
+  VLLM_USE_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-Fp8-CT-Block-deepgemm-deepep-ll.yaml

@@ -0,0 +1,8 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel --all2all-backend deepep_low_latency --disable-uvicorn-access-log"
+env:
+  VLLM_USE_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-Fp8-CT-Block-deepgemm.yaml

@@ -0,0 +1,8 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel"
+env:
+  VLLM_USE_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-NvFp4-CT-fi-cutedsl-deepep-ll.yaml

@@ -0,0 +1,5 @@
+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 --all2all-backend deepep_low_latency --moe-backend=flashinfer_cutedsl"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutedsl-deepep-ll.yaml

@@ -0,0 +1,5 @@
+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 --all2all-backend deepep_low_latency --moe-backend=flashinfer_cutedsl"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_cutlass"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_trtllm"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/config-b200.txt

@@ -0,0 +1,12 @@
+Qwen3-30B-A3B-NvFp4-CT-fi-cutedsl-deepep-ll.yaml
+Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutedsl-deepep-ll.yaml
+Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
+Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
+Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm-deepep-ht.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm-deepep-ll.yaml
+Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm.yaml
+Qwen3-30B-A3B-Fp8-CT-Block-deepgemm-deepep-ht.yaml
+Qwen3-30B-A3B-Fp8-CT-Block-deepgemm-deepep-ll.yaml
+Qwen3-30B-A3B-Fp8-CT-Block-deepgemm.yaml
+Qwen3-30B-A3B-BF16-triton.yaml

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-BF16-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "meta-llama/Llama-4-Scout-17B-16E-Instruct"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-BF16-triton.yaml

@@ -0,0 +1,6 @@
+model_name: "meta-llama/Llama-4-Scout-17B-16E-Instruct"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
+

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "nvidia/Llama-4-Scout-17B-16E-Instruct-FP8"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml

@@ -0,0 +1,5 @@
+model_name: "nvidia/Llama-4-Scout-17B-16E-Instruct-FP8"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_trtllm"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-marlin.yaml

@@ -0,0 +1,7 @@
+model_name: "nvidia/Llama-4-Scout-17B-16E-Instruct-FP8"
+accuracy_threshold: 0.92
+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"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-triton.yaml

@@ -0,0 +1,5 @@
+model_name: "nvidia/Llama-4-Scout-17B-16E-Instruct-FP8"
+accuracy_threshold: 0.92
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=triton"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-BF16-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "mistralai/Mixtral-8x7B-v0.1"
+accuracy_threshold: 0.58
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-BF16-triton.yaml

@@ -0,0 +1,5 @@
+model_name: "mistralai/Mixtral-8x7B-v0.1"
+accuracy_threshold: 0.58
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-Fp8-AutoFp8-fi-cutlass.yaml

@@ -0,0 +1,6 @@
+# TODO(rob): enable
+# model_name: "amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV"
+# accuracy_threshold: 0.62
+# num_questions: 1319
+# num_fewshot: 5
+# server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-Fp8-AutoFp8-triton.yaml

@@ -0,0 +1,5 @@
+model_name: "amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV"
+accuracy_threshold: 0.62
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml

@@ -0,0 +1,5 @@
+model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8"
+accuracy_threshold: 0.29
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_trtllm"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4"
+accuracy_threshold: 0.29
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-BF16-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-BF16-triton.yaml

@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm.yaml

@@ -0,0 +1,8 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+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_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml

@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_trtllm"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-marlin.yaml

@@ -0,0 +1,7 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+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"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-triton.yaml

@@ -0,0 +1,7 @@
+model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=triton"
+env:
+  VLLM_USE_DEEP_GEMM: "0"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-deepgemm.yaml

@@ -0,0 +1,8 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
+env:
+  VLLM_USE_DEEP_GEMM: "1"
+  VLLM_USE_DEEP_GEMM_MOE: "1"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-fi-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-marlin.yaml

@@ -0,0 +1,7 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+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"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-triton.yaml

@@ -0,0 +1,7 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=triton"
+env:
+  VLLM_USE_DEEP_GEMM: "0"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Channel-marlin.yaml

@@ -0,0 +1,7 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-dynamic"
+accuracy_threshold: 0.85
+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"

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Channel-vllm-cutlass.yaml

@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-FP8-dynamic"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_cutlass"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_trtllm"

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

@@ -0,0 +1,7 @@
+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"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=cutlass"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_cutlass"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=flashinfer_trtllm"

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

@@ -0,0 +1,7 @@
+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"

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

@@ -0,0 +1,5 @@
+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 --moe-backend=cutlass"

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

@@ -0,0 +1,17 @@
+Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml
+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-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
+Llama-4-Scout-BF16-fi-cutlass.yaml
+Llama-4-Scout-BF16-triton.yaml
+Mixtral-8x7B-BF16-fi-cutlass.yaml
+Mixtral-8x7B-BF16-triton.yaml
+Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
+Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml

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

@@ -0,0 +1,12 @@
+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-triton.yaml
+Qwen3-30B-A3B-Fp8-CT-Channel-marlin.yaml
+Qwen3-30B-A3B-Fp8-CT-Channel-vllm-cutlass.yaml
+Qwen3-30B-A3B-BF16-fi-cutlass.yaml
+Qwen3-30B-A3B-BF16-triton.yaml

third_party/vllm/tests/evals/gsm8k/configs/moe-refactor/config-test.txt

@@ -0,0 +1 @@
+Qwen3-30B-A3B-NvFp4-CT-marlin.yaml