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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: KV Cache Read/Write Index Corruption Under Concurrent Prefill of Variable-Length Sequences (vLLM V1, FlashInfer)
- [Feature][Performance]: Kimi K2.5: 2.4x tokenization overhead from slow HF pipeline
- [Bug]: Gemma 4 26B MoE NVFP4 fails under tensor-parallel-size 2 across all available MoE backends
- fix(reasoning): translate reasoning_effort in nemotron_v3 parser
- [BugFix] Fix streaming tool call empty fields with MTP: Pydantic null serialization + qwen3coder early return
- fix(tool-parser): preserve "none"/"nil" strings as valid enum values in minimax_m2
- [Bugfix] Fix glm4_moe_tool_parser._is_string_type for /v1/responses FunctionTool format
- [Performance]: [Bug]: meet same thread as registerClien when start_profile
- Pass extra_config to the constructor of LMCacheMPXXXAdapter
- [Bugfix] - Enforce enable_chunked_prefill=False even if long_prefill_token_threshold is set > 0
- Docs
- Python not yet supported