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
- [V1][Core] Add public build_full_block_hash_chain helper for offline prefix-cache analysis
- [Bug]: [MRV2] MTP speculative decoding crashes with cudaErrorStreamCaptureUnsupported during CUDA graph capture
- Fixes Issue #48749, Co-authered by Google Antigravity
- [Bug]: Qwen3.5-35B FP8 kv cache is slower than BF16 kv cache on SM90 (Hopper)
- [Kernel] ReplaySSM: cache SSM inputs for faster Gated DeltaNet standard decode
- [Bugfix][Spec Decode] Fix multi-layer Qwen3.5 MTP dispatch
- [Bugfix][Model] Fix Qwen3.5 MTP multimodal weight loading
- [Bugfix][Tool Parser] Phi4Mini: don't drop tool calls with nested-array arguments
- [Bug]: "There are significant spike issues in TTFT" with Kimi-K2.6-NVFP4
- fix: defer optional transformers model imports
- Docs
- Python not yet supported