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
- [Feat][Frontend] Add Watchdog for Engine and Worker Monitoring
- [Feat][MM Cache] Skip media loading & decoding if UUID based cache lookup succeeds
- [Quantization] Enable shared expert fusion compatibility with online `shared_expert` quantization (showcase: along Quark MXFP4 routed experts)
- [Perf][DSpark] KV-only context insert and fused kv_norm
- [Bugfix] Preserve GDN recurrent state on zero-draft speculative decode steps
- [Performance][Model] DeepSeek-V4: reuse fused post residual for aux hidden states
- [Docker] Compile Python bytecode at image build time
- [Bugfix][NIXL] Recover locally invalidated pull peer metadata
- [6/N] HiSparse: support direct GPU landing for P/D transfers
- [Bugfix][Spec Decode] Allow num_speculative_tokens to default from draft config for MTP
- Docs
- Python not yet supported