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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI Failure]: MI300 MoE Kernels Multi-GPU - MoriEPv2 combine block_num 304 exceeds xdb_flag_slots 256 in test_modular_kernel_combinations.py
- [Bugfix][Benchmark] Derive forward benchmark batch budget from cases
- [Feat] Add HALOps as an opt-in MXFP8 GEMM backend for Blackwell
- [Bugfix][Frontend] Reject API keys for the Python gRPC server
- [Bugfix][P/D] Reject P/D kv_transfer_params with several prompts
- [Feature][Frontend] Add metadata value to mm_payload on render requests
- [Bug]: Quark `exclude` entries written as weight names (e.g. `mtp.fc.weight`) are silently never matched, breaking MTP speculative decoding
- [Perf][Core] Optimize sliding-window prefix cache lookup with stride jumping
- [Quantization] Extend int8_per_channel_weight_only to LinearBase.
- [Perf][Sampler] Histogram-bracket top-p for large p-only batches
- Docs
- Python not yet supported