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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][LoRA] Avoid block_n=128 for lora_expand on Hopper
- [Bug]: Runtime-varying tl.constexpr params force Triton kernel recompiles on the serving path (unified attention MAX_MM_RANGES et al.)
- fix: Add FP8 type dispatch to per_token_group_quant_8bit for transformers backend
- [Bugfix] Surface DCP-compatible backends in the DCP error message
- [Bugfix] Gemma4 parser: don't truncate string args at interior `<|"|>` tokens
- [Bugfix] MiniMax M3 reasoning parser: treat non-leading <mm:think> as content
- [MRV2][Spec Decode] Adaptive Speculative Decoding - Initial Support
- [Feature] Support prompt cache retention policies for tiered KV offloading
- [BugFix] Fix FunctionGemma streaming tool-call arguments corrupted once a 2nd key arrives
- [BugFix] Fix Jamba tool parser deleting all occurrences of the streamed prefix on tool transition
- Docs
- Python not yet supported