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 supported46 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Misc] Improve DCP error messages with actionable guidance
- feat: auto-calculate optimal max_num_seqs via startup decode profiling
- [Core][Feat] Add max-waiting-queue-time parameter to reject requests
- [Bugfix] Fix KV cache sizing and allocation for hybrid Mamba/attention models
- fix: apply redundancy_buffer_memory to KV cache allocation
- fix(cpu_worker): Fix list index out of range in omp_cpuids_list for multi-node distributed inference
- [Benchmark] Add iteration benchmark with server-side step stats, trac…
- [LoRA] Support FP8 LoRA E2E inference-dense model
- [ROCm][Perf] Skip head repeat_interleave for AITER MLA decode with BF16 KV cache
- Speculative/MTP draft config appears to drop target --hf-overrides (breaks long-context YaRN/RoPE extension)
- Docs
- Python not yet supported