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

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

humming

moe-refactor

moe-refactor-dp-ep

DeepSeek-R1-DP.yaml

DeepSeek-R1-DP_MI325.yaml

DeepSeek-R1-DP_MI355.yaml

DeepSeek-R1-TP.yaml

DeepSeek-R1-TP_MI325.yaml

DeepSeek-R1-TP_MI355.yaml

DeepSeek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml

DeepSeek-V2-Lite-Instruct-FP8.yaml

DeepSeek-V3.2-DP.yaml

DeepSeek-V3.2-DP_MI325.yaml

DeepSeek-V3.2-DP_MI355.yaml

DeepSeek-V3.2-TP.yaml

DeepSeek-V3.2-TP_MI325.yaml

DeepSeek-V3.2-TP_MI355.yaml

DeepSeek-V4-Flash-DSpark-AITER-TEP4.yaml

DeepSeek-V4-Flash-DSpark-confidence-TEP4.yaml

DeepSeek-V4-Flash-DSpark-FP8-TP4-ROCm.yaml

DeepSeek-V4-Flash-NVFP4.yaml

DeepSeek-V4-Pro-NVFP4.yaml

DiffusionGemma-26B-A4B-it-FP8-dynamic.yaml

gemma-4-E4B-it-qat-mobile-ct.yaml

GLM-5.2-NVFP4-HiSparse.yaml

GLM-5.2-NVFP4-TP1-PCP4-DCP4-EP.yaml

GLM-5.2-NVFP4-TP1-PCP4-EP.yaml

GLM-5.2-NVFP4-TP2-PCP2-EP.yaml

Kimi-K3-pruned75-DSpark-AITER-TP4.yaml

Kimi-K3-pruned75-DSpark-TP4.yaml

Laguna-XS-2.1-INT4.yaml

Laguna-XS.2-NVFP4.yaml

Llama-3-8B-Instruct-nonuniform-CT.yaml

Llama-3.2-1B-Instruct-INT8-CT.yaml

models-blackwell-ep-mi355.txt

models-blackwell-ep.txt

models-blackwell.txt

models-gfx950-large.txt

models-gfx950-small.txt

models-h200-deepseek-r1-dp.txt

models-h200-deepseek-r1-tp.txt

models-h200-deepseek-v32-dp.txt

models-h200-deepseek-v32-tp.txt

models-h200-nemotron-3-super.txt

models-hisparse.txt

models-mi355-deepseek-r1-dp.txt

models-mi355-deepseek-r1-tp.txt

models-mi355-deepseek-v32-dp.txt

models-mi355-deepseek-v32-tp.txt

models-mi355-nemotron-3-super.txt

models-mi3xx-fp8-and-mixed.txt

models-mi3xx.txt

models-pcp.txt

models-qwen35-blackwell.txt

models-qwen35-mi355.txt

models-small-tp-mi355.txt

models-small-tp.txt

models-small.txt

models-spec-decode-rocm.txt

models-spec-decode.txt

models-turboquant-k3v4nc-rocm.txt

models-turboquant-k3v4nc.txt

models-turboquant-k8v4-rocm.txt

models-turboquant-k8v4.txt

models-turboquant-t3nc-rocm.txt

models-turboquant-t3nc.txt

models-turboquant-t4nc-rocm.txt

models-turboquant-t4nc.txt

models-watermark-dspark-tp2.txt

models-watermark.txt

Nemotron-3-Super-120B-A12B-BF16.yaml

Nemotron-3-Super-120B-A12B-BF16_MI355.yaml

Nemotron-3-Super-120B-A12B-FP8.yaml

Nemotron-3-Super-120B-A12B-FP8_MI355.yaml

Nemotron-3-Super-120B-A12B-NVFP4-MI355.yaml

Nemotron-3-Super-120B-A12B-NVFP4.yaml

Qwen1.5-MoE-A2.7B-Chat-INT8.yaml

Qwen1.5-MoE-W4A16-CT.yaml

Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml

Qwen3-0.6B-FP8.yaml

Qwen3-1.7B-MXFP4.yaml

Qwen3-30B-A3B-MXFP4-AITER-TP2-online.yaml

Qwen3-30B-A3B-MXFP4-AITER-TP2.yaml

Qwen3-30B-A3B-MXFP4A16.yaml

Qwen3-30B-A3B-NVFP4-quark.yaml

Qwen3-30B-A3B-NVFP4.yaml

Qwen3-30B-A3B-Thinking-2507-FP8.yaml

Qwen3-30B-A3B-Thinking-2507-PTPC-FP8.yaml

Qwen3-4B-FP8-DSpark-watermark-TP2.yaml

Qwen3-4B-TQ-k3v4nc-ROCm.yaml

Qwen3-4B-TQ-k3v4nc.yaml

Qwen3-4B-TQ-k8v4-ROCm.yaml

Qwen3-4B-TQ-k8v4.yaml

Qwen3-4B-TQ-t3nc-ROCm.yaml

Qwen3-4B-TQ-t3nc.yaml

Qwen3-4B-TQ-t4nc-ROCm.yaml

Qwen3-4B-TQ-t4nc.yaml

Qwen3-Next-80B-A3B-NVFP4-EP2-CT-MI355.yaml

Qwen3-Next-80B-A3B-NVFP4-EP2-MTP-MI355.yaml

Qwen3-Next-80B-A3B-NVFP4-EP2.yaml

Qwen3-Next-FP8-EP2.yaml

Qwen3-Next-FP8-EP2_MI355.yaml

Qwen3.5-35B-A3B-DEP2.yaml

Qwen3.5-35B-A3B-FP8-DEP2.yaml

Qwen3.5-35B-A3B-MXFP4-AITER-TP2.yaml

Qwen3.5-35B-A3B-MXFP4-EMU-TP2.yaml

Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml

Qwen3.5-397B-A17B-NVFP4-DEP2.yaml

Qwen3.5-4B-watermark.yaml