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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: Flashinfer TRTLLM MoE for Qwen3.5
- [Bug] _warmup_prefill_kernels in qwen3_next.py leaks ~3.4 GiB GPU memory despite empty_cache()
- [Bugfix] Fix delta_text and delta_token_ids desync with stop strings
- [Kernel][Helion][1/N] Add Helion kernel for rms_norm_per_block_quant
- [Kernel][Helion][1/N] Add Helion kernel for per_token_group_fp8_quant
- Fix Qwen3.5 rope validation TypeError: list | set (#36920)
- [Bug/Regression]: CPU spikes to 100% on Multi-node (PP=2, TP=8) | Regression starting from v0.12.0
- [Bugfix] Streaming finish_reason chunk should have empty delta content
- [Bugfix] Fix unclean shutdown from ctrl-c with AR Fusion
- [Feature] Add /health/ready endpoint for GPU health verification
- Docs
- Python not yet supported