mudler/vllm.cpp

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)

367Stars on the repository
4Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

vllm.cpp AGENTS.md

01

mudler/vllm.cpp

Instructions file CodexOpenCode

Instructions for mudler/vllm.cpp, covering agents.md: the rules, start here, history is git, every change starts from an issue and spec before code.

367 yesterday A 8,119 tokens original Apache-2.0

vllm.cpp CLAUDE.md

02

mudler/vllm.cpp

Instructions file

Instructions for mudler/vllm.cpp, a project described as: a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...).

367 yesterday A 3 tokens copy · 100% Apache-2.0