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
Add a CodeTriage badge to vllm
Help out
- Issues
- Fix weight loading I/O contention and add FlashInfer autotune logging
- FlashInfer MLA decode workspace buffer overflow with decode-context-parallel
- fix(model): ensure cpu tensor contiguity during Llama4 ModelOpt weight loading
- Fix OverflowError in prompt_logprobs when external KV pre-fills prompt
- Add external metrics providers for stat logger plugins
- [ROCm][Bugfix] Hoist tt.addptr out of scf.if in fused_qk_rmsnorm
- [Bugfix] Fix DeepSeek MoE sequence-parallel layout tracking
- [Spec Decode] Fix FA3 AOT scheduler head count mismatch for DFlash/DSpark
- Rust Frontend: Add supervisor-side control channel for Elastic EP scaling
- Update workflow comments and add first-interaction action.
- Docs
- Python not yet supported