vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported51 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- V1 multiprocess engine: sporadic 0.7-2s frozen engine step once per generate batch (absent with VLLM_ENABLE_V1_MULTIPROCESSING=0)
- fix: Domino inference patches for speculators-format checkpoints
- [DCP] Add FlashInfer fused A2A backend for decode context parallelism
- [Rust Frontend] Add HTTP access log with disable and endpoint-exclusion flags
- [Bugfix] Opt out of pinned host memory for shm multimodal decode
- [RFC]: Standardize vLLM Entrypoint Error Handling
- [Bugfix] Presize shared MoE Workspace To Worst-Case Size Before Lock
- [Perf][FA4] Warm up dense (paged) FA4 attention kernels
- [RFC]: GLM-5.x thinking_token_budget defaults and regression tests
- [BugFix] Fix per-group prefix-hit divergence for hybrid Mamba + KV connector
- Docs
- Python not yet supported