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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- chore: update RunAI Model Streamer to 0.16.0
- [PERF] Vedic 4-bit quantized matmul for MLA attention — 3.5x CPU speedup
- [Misc] add option to prevent private networks access for media urls
- Spec decode with multimodal pruning gives Eagle drafter shifted embeddings but unshifted M-RoPE positions
- Add Gemma4ForSequenceClassification model
- [Feature]: Kimi K2.5/K2.6 LoRA loading support
- [Bug]: `--num-gpu-blocks-override 0` silently accepted; engine init fails with bare `AssertionError` in `BlockPool.__init__`
- [Feature]: DFlash Partial Multimodal Token Full Attention with Gemma MoE + Drafter
- Terminal Benchmark for Tool Calling (Qwen3)
- [Bugfix] precompile Triton KV-zero and slot-mapping kernels (#43009)
- Docs
- Python not yet supported