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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Frontend] Decode each streaming-input chunk after its own prompt
- [Quantization] Support ModelOpt INT8_PB_WO (per-block INT8 weight-only) linear layers
- [XPU] Support Extensible KV cache
- [Bugfix][Core] Release libgomp workers before every fork
- [Perf] SM90 FP8 scaled_mm: 64x256 tiles for M just above a multiple of 256
- [Benchmark][MoE] Add eager and graph top-k chain measurements
- [Bugfix][MoE] Keep grouped top-k weights independent of batch size
- [Bugfix][Rust Frontend] Fail incomplete and errored streams in vllm-bench
- [Bugfix][Parser] Preserve token IDs in non-streaming engine parsing
- [Perf][GLM-5.3-Flash] Add SM90 skinny GEMM plans for the BF16 decode projections
- Docs
- Python not yet supported