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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(openai): bound validation-error response size for malformed requests
- [Core] Fix EngineDeadError on late KV transfer completion
- add logs to local the garbled text issue
- [Quark] Online-requant unquantized layers via quantization_config ove…
- Fix response_format=text for speech-to-text endpoints
- [Bug]: Latest vllm is incompatible with `openai<2.25.0`
- [Bug]: False positive warning "Unexpected gate/up projection names" for non-gated MoE (Nemotron 3 Ultra / Nemotron H)
- [Bugfix] Preserve pooling token-ID state during batch reordering
- [Core][KV Connector][Mooncake] Support MRV2 prefill PCP in Mooncake
- [Bugfix] Fix false positive warning for non-gated MoE (Nemotron H)
- Docs
- Python not yet supported