.buildkite/lm-eval-harness/configs · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

DeepSeek-V2-Lite-Chat.yaml

DeepSeek-V4-Flash-MXFP4.yaml

Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml

Meta-Llama-3-70B-Instruct.yaml

Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml

Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform.yaml

Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml

Meta-Llama-3-8B-Instruct-FP8.yaml

Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml

Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml

Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml

Meta-Llama-3-8B-Instruct.yaml

Meta-Llama-3-8B-QQQ.yaml

Meta-Llama-3.2-1B-Instruct-FP8-compressed-tensors.yaml

Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml

Meta-Llama-4-Maverick-17B-128E-Instruct-FP8-MM.yaml

Meta-Llama-4-Maverick-17B-128E-Instruct-FP8.yaml

Minitron-4B-Base-FP8.yaml

Mixtral-8x22B-Instruct-v0.1-FP8-Dynamic.yaml

Mixtral-8x7B-Instruct-v0.1-FP8.yaml

Mixtral-8x7B-Instruct-v0.1.yaml

models-large-hopper.txt

models-large-rocm-tp4.txt

models-large-rocm.txt

models-large-xpu-fp8.txt

models-large.txt

models-mm-large-h100.txt

models-mm-small.txt

models-small-rocm.txt

models-small.txt

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.yaml

NVIDIA-Nemotron-3-Nano-30B-A3B-FP8-xpu.yaml

NVIDIA-Nemotron-3-Nano-30B-A3B-FP8.yaml

Qwen1.5-MoE-W4A16-compressed-tensors.yaml

Qwen2-1.5B-Instruct-FP8W8.yaml

Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml

Qwen2-57B-A14-Instruct.yaml

Qwen2.5-1.5B-Instruct.yaml

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

Qwen2.5-VL-7B-Instruct.yaml

Qwen3-235B-A22B-Instruct-2507-FP8.yaml