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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Rust Frontend] Clamp logit_bias values to the valid range
- [Fix] Replace ValueError with VLLMValidationError in chat_utils.py
- [Bugfix][Frontend] Avoid mutating OpenAI request extra args
- [Feature]: Support verbose_json for MOSS-Transcribe-Diarize
- [Bugfix][Mooncake] Order async loads after cache block copies
- [Frontend] Add verbose_json support for MOSS-Transcribe-Diarize
- [Perf][Sparse MLA] Drop the atomic contention in the index remap
- [Proposal] OpenEval Import/Export Support
- [KV Connector][Mooncake] Add MooncakePromMetrics and wire via build_prom_metrics
- Gdn ucache backend
- Docs
- Python not yet supported