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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [CI] Add DGX Spark GPQA smoke test
- [GLM-5] Fix loading of appended NextN/MTP draft layers
- [Model][Hardware][AMD][Kernel]: Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_ATTN, ROCM_AITER_FA, and ROCM_AITER_UNIFIED_ATTN
- [Bugfix]: Expose added_tokens_decoder to mistral tokenizer wrapper
- [vLLM IR] Minor improvements (#39362)
- [Bugfix]: Fix assertion in MambaManager.allocate_slots()
- [RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support
- [Model] Support per-layer sliding window attention for Qwen3
- [Core] Use standalone autograd_cache_key for compilation dedup optimization
- [Kernel] Batch invariant NVFP4 Triton MoE backend
- Docs
- Python not yet supported