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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][Hybrid] Warn when Mamba-aligned prefill chunks leave the token budget idle
- [RFC]: Native in-engine parallel beam search
- [ROCm] Fix MiniMax-M3 sparse PA KV block count
- [Bugfix] Fix FP8 NaN from per-call unit scales in ChannelWiseTorchFP8ScaledMMLinearKernel
- [KV Connector] Per-connector "enable_kv_events" switch for KV cache events
- [Bug]: ORCA endpoint-load-metrics reports only one engine's load under data parallel
- [Bugfix][Metrics] Aggregate DP engine samples in ORCA load header
- [Perf] Make DeepEP high-throughput SM count configurable
- [Bug][KV Connector] Late load-failure reports affect unrelated requests after block-ID reuse
- [Bug]: MiMo-V2 with FP8 KV cache crashes on NVIDIA SM89/SM12x: Triton DiffKV fails to compile ("K >= 32"), since v0.32.0rc0
- Docs
- Python not yet supported