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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: _compute_slot_mapping_kernel reads block_table out of bounds for cache groups whose block table is narrower than the sequence
- [Bug]: [dspark] Adaptive verification profiles a batch shape the scheduler cannot produce
- [Quantization][Autoround][XPU] Add MXFP4 Hadamard rotation support
- [Bug]: GLM-5.3-Flash on ROCm (gfx950): SparseAttnIndexerKpool.forward_hip() missing gate_score — platform guard hides a fixable gap
- [8/N] HiSparse: add DeepSeek V4 support
- [Performance] vLLM warmup does not cover C128A extra_topk=384 on SM120 sparse-MLA decode, causing SparseMlaDecodeV3Runner tactic=-1 fallback
- [MRv2][Bugfix] Initialize DCP metadata
- [Bug]: CPU KV offload (OffloadingConnector) crashes on DeepSeek-V4 MLA — flat int8 layout assumption vs padded multi-group uint8 cache
- [KV Connector] Guard align_to_block_size and empty prompt_token_ids in ExampleConnector
- Unsupported tool_choice in Responses API (Harmony/gpt-oss) returns HTTP 501, should be 4xx
- Docs
- Python not yet supported