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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: V1 streaming-session rebuild leaves stale prefix-cache block hashes and can produce incorrect output
- [Perf] Add mm_tensor_ipc=cuda_ipc TP-aware GPU transport
- [Bug]: MTP speculative decoding is broken with pipeline parallelism (PP>1) — three distinct failures
- [Bug]: Token truncation leaves stale Request.block_hashes and can cause incorrect KV cache hits
- [Bugfix] Fix SM100 fp8_ds_mla cache scales
- [Bugfix] MiniCPM-V 4.6: fix ViT self-attn qkv weight loading
- [Bugfix] Fix pipeline parallelism for Kimi-Linear
- [Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation
- [Core] Add `max_num_queued_reqs` and `max_num_queued_tokens` for queue size management
- [Online quantization] Add online MXFP4 quantization support
- Docs
- Python not yet supported