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
- [ROCm] Add V2 BF16 streamed PP transport
- [ROCm][MXFP4] Align the AITER W4A4 MoE intermediate size to 128
- [Bug]: Mooncake bootstrap registration timeout can leave producer startup blocked indefinitely
- [Bugfix][Tool Parser] Make step3 streaming independent of delta boundaries
- Batch-invariant matmul is not actually batch-invariant, and TF32 causes precision degradation
- [Bugfix][ROCm] Allocate topk_ids at the width AITER's topk kernels write
- [wip] support PD seperate mode for fault-tolerance
- [Bugfix][Structured Outputs] Support new-format structural tags in the guidance backend (strict/required/named tool calling)
- [Feature]: Restart Lifecycle Hooks for KV Transfer Connectors (NIXL)
- fix: reject unsupported encoder-only prefix caching
- Docs
- Python not yet supported