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
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Accumulate ranks in absolute order in 2-stage custom all-reduce
- [Bug]: Scale-out token path breaks stop strings: stop text leaks into derendered output (include_stop_str_in_output ignored) and --tokens-only silently disables stop entirely
- [ROCm][Perf] Tile DSV4 inverse RoPE for sparse prefill
- [ROCm][Opt] DeepSeek-V4 optimizations
- [Kimi-K3][Perf] Overlap shared-output all-reduce with routed experts
- [Bug] GLM-5.3 hybrid (nvfp4, GB10/sm121, TP2): concurrent batching corrupts non-ASCII generation — fragment-token state poisoning + silent DecodeStream FFFD flush
- [Docs] Add ecosystem kernels index skill
- [Bugfix][Benchmark] Keep all requests in prefix-repetition samples
- [Bugfix] Validate activation schemes for Marlin and Triton WNA16 MoE
- [Bugfix] Make online FP8 MoE experts batch-invariant under VLLM_BATCH_INVARIANT
- Docs
- Python not yet supported