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 supported44 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Corrects estimate of torch memory use causing OOM due to incorrect KV cache space estimation when sleep mode on (Fixes #40256)
- [Bugfix][Gemma4] Fix vision fp16 overflow causing <pad> output
- [vLLM IR] Update the pre commit to enforce imports of vllm
- docs: expand load_weights guide with AutoWeightsLoader and manual patterns
- [ROCm] Add missing gfx1152, gfx1153, and enable all gpu arch to AITER in docker
- [Perf] Integrate flash-maxsim Triton kernels for late-interaction scoring
- [RFC]: Unified ModelOpt Quantization in vLLM
- [torch.compile] Remove layer name from unified_kv_cache_update / unified_mla_kv_cache_update to fix cold-start (#33267)
- [RFC]: Add API to restore free_block_queue allocation order for long-running RLHF / rollout sessions
- [torch.compile] refactor config hashing through compile_factors and normalization
- Docs
- Python not yet supported