GitHub - voipmonitor/llm-pytorch-blackwell: Bleeding-edge LLM inference Docker image for RTX Blackwell (SM120) — PyTorch nightly + vLLM + SGLang + FlashInfer

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
backup_pcie		backup_pcie
configs		configs
patches		patches
scripts		scripts
.dockerignore		.dockerignore
Dockerfile		Dockerfile
build.sh		build.sh
docker-compose.yml		docker-compose.yml
entrypoint.sh		entrypoint.sh
jit-cache-invalidate.sh		jit-cache-invalidate.sh
warmup_jit.py		warmup_jit.py