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
- [Usability]: Unify cache gathering kernels (gather_and_maybe_dequant_cache, cp_gather_cache, cp_gather_and_upconvert_fp8_kv_cache)
- [Bug]: HTTP API multimodal embedding causes image_pad token duplication, producing incorrect results
- [Usage]: Mistral-Nemo-12B function calls returned in content instead of tool_calls
- [Bug]: [ROCm] Kimi-K2.5 produces incorrect results on AMD MI308X
- [Bugfix][Feature] Fix Anthropic Message Stream Converter and Support Thinking Block
- [ROCm] [aiter] Split KV cache update for AiterFlashAttention
- [Misc] Add deprecated environment variable utilities
- [Perf][Kernel] Add faster topKperRow decode kernel for DeepSeek-V3.2 sparse attention
- [Bug]: Hadamard Transform R4 weight length assertion
- [Bug]: DeepSeek-V3.1 with fp8 KV Cache causes illegal memory access at concurrency ≥ 5 in `serve_benchmark`
- Docs
- Python not yet supported