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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature] TRITON_ATTN add INT8 per-tensor KV cache quantization
- [Bugfix][CI] Enable tool parser tests for Qwen3 Coder, fix function call detection
- Hoist DCP scratch tensors to top-level allocation
- [Bugfix] Enable BitsAndBytes support for Mamba-2
- Add NVFP4 all-gather GEMM fusion for AsyncTP
- [vLLM IR] port activation ops (fatrelu_and_mul, relu2, gelu_and_mul_sparse, swigluoai_and_mul)
- [Bugfix] Fix collect_env.py crash on non-Linux platforms due to unconditional assert
- [CPU][RISC-V] Add fp8 tag stubs to satisfy GCC 15 -Wtemplate-body
- [CPU][RISC-V] Use compiler-provided __riscv_zvfh / __riscv_zvfbfmin instead of hand-rolled macros
- [Perf] Cache rotary position IDs in Qwen2-VL vision encoder
- Docs
- Python not yet supported