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
- [Bugfix][Core] Hand off a producer's partial-tail boundary state on preemption
- fix: resolve --cc dotted-arg to registered option string
- [Docs] max_num_seqs is bounded by the Mamba cache pool on hybrid models
- [Bugfix] Reject quantized KV cache for encoder-only attention
- [Bug]: guidance backend rejects tool-calling structural tags (KeyError: 'triggers') — strict/required/named tool_choice broken
- [Kernel][Quant] Machete W4A8 ldmatrix.s8.s4
- [NIXL] Use stride desc API
- [Bug]: MoE LoRA one-shot path rejects max_lora_rank=256 although LoRAConfig accepts it
- [Bugfix][LoRA] Fall back for high-rank MoE LoRA
- [Bugfix][Scheduler] Restore priority order for streaming continuations
- Docs
- Python not yet supported