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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [V1, V2] Add temperature for prompt logprobs
- [Distributed] Add OfflineState bloom-filter cooperative caching KV connector
- [Bugfix] Add autotuning guard to all unprotected FlashInfer MoE kernels
- [Bugfix] Align routed_experts with streamed and final output token spans
- Unwrap fused_moe (control via env var) for non-DP-EP cases
- fix(moe): detect and handle unquantized MoE weights in NVFP4 checkpoints
- [Bugfix][sleepmode] Serialize GPU VMM operations to fix sleep/wakeup race condition
- [Feature][Cleanup]: Optimize token data structures (list[int] to TokenArray)
- feat: Standardize load_weights API via AutoWeightsLoader
- [CI][Bugfix][AMD][ Ensure weights created when using emulating OCP MXFP4
- Docs
- Python not yet supported