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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI/Build] Keep a plain CUDA arch requested alongside its a/f variant in cuda_archs_loose_intersection
- [Bug]: Garbled output for GLM 5.3 Flash when weights loaded with run:ai distributed streamer
- [Bugfix] GLM-5.3-Flash: keep FP8 weight/scale pairs across load_weights calls
- [Bugfix][Frontend] Honor stop_token_ids on the Responses API
- [Bugfix][ROCm][Model] Quantize GLM-5.3-Flash indexer query with platform fp8 dtype
- fix: Pixtral compat with transformers 5.17
- fix(mamba): tolerate num_accepted=0 in the CPU GDN spec path
- [Perf][Qwen] Inline zero padding kernel during MTP decodes (1% decode speedup)
- docs: fix 'allows to' grammar in Quark quantization docs
- [Bug]: ROCm Stack DeepSeekv4.1 Flash Issue spamming logs with GLUON backend not available. Using TRITON backend!!!
- Docs
- Python not yet supported