dhruvhead/qwen38-27b-rtx3090 - Morph

SIGN IN SIGN UP

dhruvhead / qwen38-27b-rtx3090 UNCLAIMED

0 0 0 Python

4 branches

kv-cache llm-inference local-llm quantization qwen qwen3 rtx-3090 speculative-decoding vllm

mhenrichsen README: quick start first, one command per mode

69ba4d0 · 3d ago · 119 Commits

	.github
	batch
	bench
	docker
	docs
	drafter
	kvarn
	patches
	prepare
	single-user
	.dockerignore		284 B
	.gitattributes		224 B
	.gitignore		126 B
	docker-compose.yml		2.7 KB
	Dockerfile		1.8 KB
	LICENSE		11.1 KB
	README.md		38.5 KB
	verify.sh		11.5 KB