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] Fix use_existing_torch.py stripping unrelated torch-* packages
- [Bugfix][LoRA] Disable encoder graphs for tower LoRA
- [bot] Enable Gemma4-E4B inference on Intel XPU with per-layer head_dim routing
- [Bugfix][MoE] Pad MoE activations inside the custom op to fix CUDA-graph corruption
- [Bugfix] Fix Qwen3 XML numeric fallback warnings
- [Bugfix] Muse Glimmer: apply structured outputs to the to=user answer
- [Bugfix][Frontend] Honor tool declarations on developer/system messages
- Fix `max_offload_tokens` assertion error.
- [ROCm][gfx942] DSv4 sparse-attn indexer: native fp8 MFMA + corrected LDS occupancy gate
- [Bug]: VLLM_BATCH_INVARIANT=1 crashes NVFP4 models: emulation break_fp4_bytes device mismatch (lookup table on CPU, indices on GPU)
- Docs
- Python not yet supported