tests/evals/gsm8k/configs/moe-refactor · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

config-b200-shard-0.txt

config-b200-shard-1.txt

config-b200-shard-2.txt

config-b200-shard-3.txt

config-b200.txt

config-h100-shard-0.txt

config-h100-shard-1.txt

config-h100-shard-2.txt

config-h100-shard-3.txt

config-rocm-shard-0.txt

config-rocm-shard-1.txt

config-rocm-shard-2.txt

config-rocm-shard-3.txt

config-test.txt

DeepSeek-V4-Flash-deepgemm-mega-moe.yaml

Llama-4-Scout-BF16-fi-cutlass.yaml

Llama-4-Scout-BF16-triton.yaml

Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml

Llama-4-Scout-Fp8-ModelOpt-fi-cutlass.yaml

Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml

Llama-4-Scout-Fp8-ModelOpt-marlin.yaml

Llama-4-Scout-Fp8-ModelOpt-triton.yaml

Mixtral-8x7B-BF16-fi-cutlass.yaml

Mixtral-8x7B-BF16-triton.yaml

Mixtral-8x7B-Fp8-AutoFp8-fi-cutlass.yaml

Mixtral-8x7B-Fp8-AutoFp8-triton.yaml

Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml

Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml

Nemotron-Nano-30B-NvFp4-ModelOpt-vllm-cutlass.yaml

Qwen3-30B-A3B-BF16-fi-cutlass.yaml

Qwen3-30B-A3B-BF16-triton-rocm.yaml

Qwen3-30B-A3B-BF16-triton.yaml

Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm.yaml

Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml

Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.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-fi-cutlass.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-NvFp4-CT-fi-cutlass.yaml

Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml

Qwen3-30B-A3B-NvFp4-CT-marlin.yaml

Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml

Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml

Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml

Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml

Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml