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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(reasoning): prevent streaming end-token desync in base and other parsers
- [Bug]: Gemma 4 FP8 dynamic quantization = gibberish output
- [Feature]: Speculative Prefill — Draft-Assisted Sparse Prefill for TTFT Reduction
- [Docs] document cache salting for prefix cache timing side-channel mitigation
- [Bug]: Certain Ranks Take a Look Time to Load Weights
- vLLM 0.19 may lose tool calls for Qwen/Qwen3.5-35B-A3B-FP8 when XML tool_call is emitted inside <think>
- [ROCm][CI] Fix fused RMS norm FP8 quant test on MI250 (gfx90a)
- [Transformers/Bugfix] Fix Gemma4 MoE top_k lookup + duplicate kv_seqlens in op schema
- [Bugfix] Fix gemma4_utils._parse_tool_arguments truncating strings with internal quotes
- [ROCM] Optimize all-reduce performances.
- Docs
- Python not yet supported