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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: triton unified_attention reads block_table out-of-bounds past the used columns
- [LoRA] Fail loudly on kv_b_proj adapters for MLA models
- [Bugfix] Fix OOB write in fused_recurrent_gated_delta_rule non-inplace final_state
- [Bugfix] Fix out-of-bounds read in kernel_unified_attention block_tab…
- [Model] Add LoRA support for PaddleOCR-VL
- [Kernel][Perf] Tune small packed GDN decode shapes on SM89
- [MRV2][Spec Decode] Optimize DSpark with local argmax reduction
- [Bugfix][MRV2][Spec Decode] Sync standalone draft token counts across DP ranks
- [CPU] Cap auto OpenMP thread binding at the cgroup CPU quota
- [DARFT][Core][DP] Add an opt-in cross-DP prefill delayer (--dp-prefill-delayer)
- Docs
- Python not yet supported