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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Auto-adjust max num seqs mamba
- [Nixl][PD] Lease renewal TTL KV blocks on P
- fix(tokenizer): guard reasoning_effort for Mistral tokenizer
- [Bugfix][Gemma4] Fix k_eq_v full-attention projection layout
- [CPU] Add FP8 W8A16 MoE support
- [Installation] Make bitsandbytes, runai-model-streamer, and mamba-ssm optional for macOS
- [XPU] Fallback when torch.xpu mem_get_info is unsupported on integrated Intel GPU
- [torch.compile] Replace depyf with custom graph-dump
- [Bugfix] V1 Ray: sync `global_rank` in `adjust_rank` for PP > 1
- Lazy recovery evaluation for speculative rejection sampling
- Docs
- Python not yet supported