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
- [Bugfix][Model] Prefill DiffusionGemma image tokens bidirectionally
- [Bugfix][Spec Decode] Use KV-only rope insert for DeepSeek-V4/V4.1 DSpark context KV
- [Perf][MoE] Backport triton#10875 to the bundled triton_kernels v3.5.1
- [Qwen3.5] FP16 partial sums for the deferred row-parallel all-reduces
- [Bugfix][Qwen3.5] Use vllm.ir RMSNorm below SM80 instead of FlashInfer JIT
- [GLM 5.3 Perf] enable fp8 kv cache for glm 5.3 flash draft model, 790MB GPU memory saved each rank
- [Bug]: vllm/vllm-openai:muse-spark-open needs to be rebuilt with the issue fixed in #62374
- [Bugfix][MoE][LoRA] Align expert selection with target_modules
- [Bugfix][Tool Parser] gemma3_pythonic: emit argument separators so rendered tool calls parse
- [CI][ROCm] Run EP Weight Filter with EPLB on MI355
- Docs
- Python not yet supported