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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CPU][Zen] Give the int8 MoE experts slack for the in-place reorder
- [Bugfix][Frontend] Continue final assistant messages in Anthropic requests
- [Core][DP] Add a DP-global prefill gate for prefill_schedule_interval
- [Bugfix][Spec Decode] Inkling MTP: share the target embedding under PP > 1
- [Perf][MoE] Select full-warp top-k rows with redux.sync and keep selections in registers (SM80+)
- [ROCm][Attention] Accelerate ROCm Prefill Attention with FP8 Triton Kernels
- [Core][Metrics] Export deferred waiting requests by the reason they were deferred
- [Perf][SM90] Score only candidate blocks in the DSv4.1 decode indexer
- [Bugfix][Tool Parser] Preserve format-only structured outputs under auto tool choice with parser default strict level
- [ROCm][Perf][Qwen4Exp] Tile QSA indexer scoring and skip invisible columns
- Docs
- Python not yet supported