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
- [Bugfix][DP] add_dp_placement_groups does not require ray[default]
- [Spec Decode] Fix Hybrid Mamba KV-cache admission for dynamic K
- [Bugfix][NIXL] Dedup transfer regions by (base_addr, block_len)
- [Bugfix] Copy unaligned packed slices before dtype view
- [Perf][Attention][PCP] Reuse MLA context across PCP virtual rows
- [Bug]: Decode throughput drops ~3.3x from 0.26.0 to 0.29.0 on H100 (Qwen3.6-35B-A3B-FP8, same config, same backends)
- [Bugfix][Scheduler] Update structured output state for streaming sessions
- [Bugfix] Make Lark-to-EBNF quote handling escape-aware
- [KVConnector][MoRIIO] Support K3 DSpark hybrid READ
- [Bugfix] Sync FlashInfer autotune cache across ranks on the v1 path
- Docs
- Python not yet supported