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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Realtime transcription completes but server never sends transcription.done when final commit is received during slow streaming
- [Feature]: Add tool_choice="required" support for GPT-OSS Harmony models
- [Feature]: We propose the official development and maintenance of a VLLM integration or plugin within Dify.
- [RFC]: Sparse attention KV cache offloading to support longer sequence length
- [Kernel] FlashInfer: switch allreduce fusion to unified API
- [Installation]: vllm as submodule results in unbuildable docker images due to setuptools-scm and docker context
- [Installation]: building docker cpu image with VLLM_CPU_DISABLE_AVX512=true (or on any x86_64 CPU without AVX512) fails to compile mla_decode.cpp because BFloat16 has no AVX2 fallback
- [Bug] [torch 2.10] test_routed_input_transform_inside_vs_outside failing
- [RFC]: Add an option to use NCCL-based symmetric memory when pytorch symmetric memory is applied
- [BugFix][kv_offload] Fix offloading decodes with async scheduling
- Docs
- Python not yet supported