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
- [Bug]: `prompt_logprobs` depends on request order when prefix caching is enabled
- [CI Failure]: mi300_1: Multi-Modal Models (Extended Generation 2)
- [Bug]:Qwen3.5 with reasoning-parser returns non-standard tool call format when enable_thinking=true
- [Frontend] Improve interactive input line editing
- [Bug] Gemma4ToolParser streams incorrect float values (e.g., 108.2 → 108.02)
- Bump the minor-update group across 1 directory with 142 updates
- [Bug]: runai_streamer + MTP drafter fails to load weights from model_streamer local cache
- Gemma 4 + DFlash incompatible: MTP-specific backend propagation forces TRITON_ATTN on independent (DFlash) drafters
- [Spec Decode] Allow DFlash drafter to autoselect non-causal-capable backend on Gemma 4
- [MM][Perf][CG] Support ViT full CUDA graph for Kimi-VL
- Docs
- Python not yet supported