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 supported49 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [KV Offload] Add TieringAdmissionPolicy skeleton (factory/base/always)
- [Frontend] [Parser] Migrate llama3_json/llama4_json to the streaming parser engine
- [Memory] Measure complete CUDA graph capture footprint for KV budgeting
- [XPU][MoE] Resize batched Triton MoE tiles and change grid order
- [XPU] Batch LoRA slice processing to cut Python‑level launch latency
- [Bugfix][Spec Decode] Route DFlash fused context-KV projection through quant_method for quantized drafters
- [Bug]: No viable structured-outputs backend for Kimi-K2.6 + EAGLE3 on v0.26.0: xgrammar bitmask desync kills the engine, outlines compile-timeout leaks threads until OOM, guidance rejects the slow tokenizer
- [ROCm] Fix misrouting race-condition in multi-decode P/D disagg with mori-io
- [Bug]: Inkling-Small structured-output request returns 500 ("grammar rejected tokens [200028]")
- [Bug]: xlam tool parser: streamed tool-call arguments duplicated by end-of-stream flush; markers/JSON leak into content
- Docs
- Python not yet supported