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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: cudaErrorIllegalAddress crash when enabling `--performance-mode throughput` for zai-org/GLM-4.7-FP8 under load
- [Bugfix] Fix engine crash when structured output grammar compilation fails with auto backend
- [Feature] Feat(structured-outputs): expose xgrammar bitmask backend selection via platform interface
- [Bugfix] Zero-init ROCm MLA attention output buffers for graph padding
- [Metrics] Add Prometheus counter for CUDA graph mode
- [KVConnector] Support 3FS KVConnector
- [Bugfix] fixd issue#37343: prevent TTFT regression by adding batched logprobs budget to scheduler
- [NIXL][Mamba][2/N] Heterogeneous TP : chunk-interleaved layout
- [Bug]: 0.17.1 - vllm serve deepseek-ai/DeepSeek-OCR-2 on H100 crashes during Capturing CUDA graphs (decode, FULL)
- [Feat][RL] IPC weight sync optimizations: multigpu support and chunked packed tensors
- Docs
- Python not yet supported