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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: /v1/messages renders consecutive assistant messages as separate turns
- [ROCm] MiniMax-M3: allow the AMD monokernel decode on MiniMax-M3.1
- [Kernel] Add opt-in NVFP4 activations for long prefills to b12x NVFP4 W4A16 linears
- [RFC]: Group-wide LoRA admission and residency for distributed MoE serving
- [RFC]: TokenGate integration into vLLM
- [ROCm][Perf][GLM-5.3-Flash] Split decodes off the AITER FlashKDA prefill on gfx950
- [KV Connector] Spec-driven TP slicing for NIXL KV transfers
- [Bugfix][MoE] Use the prepared b12x API for compact N64 W4A8 MXFP4 experts
- [Spec Decode] Support draft_lm_head_quantization for DFlash
- [Feature][KV Connector][Mooncake] Export store usage metrics for MooncakeStoreConnector
- Docs
- Python not yet supported