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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Fix FullAttentionSpec.max_memory_usage_bytes() to respect sliding_window
- Fix Cohere ASR failing to load when librosa is not installed
- fix: allow HMA with KV events when explicitly enabled
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
- Fix engine_id collision + MoRIIO robustness for multi-node disagg DP
- [RFC]: Handle GDN prefill kernel JIT compilation failures - seeking community input
- [Bug]: FlashInfer CUTLASS MoE backend causes CUDA illegal memory access on H100 during CUDA graph capture (Qwen3-Next-80B BF16)
- [Feature]: Can you achieve this
- [RFC]: Selective KV Cache offload
- [Performance] DSV3.2 Indexer: Overlap indexer op || q_b_proj + MLA RoPE on separate CUDA streams
- Docs
- Python not yet supported