A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 07:00 UTC
main
Fix open_collective value in FUNDING.yml (#10426)
Andrew Nesbitt committed almost 2 years ago
[Doc] Add documentation for Structured Outputs (#9943)
ismael-dm committed almost 2 years ago
[5/N][torch.compile] torch.jit.script --> torch.compile (#10406)
youkaichao committed almost 2 years ago
[Doc] Update doc for LoRA support in GLM-4V (#10425)
B-201 committed almost 2 years ago
[Model] Remove transformers attention porting in VITs (#10414)
Isotr0py committed almost 2 years ago
[Model][LoRA]LoRA support added for glm-4v (#10418)
B-201 committed almost 2 years ago
[Model] Remove redundant softmax when using PoolingType.STEP (#10415)
Maybewuss committed almost 2 years ago
[VLM] Report multi_modal_placeholders in output (#10407)
lkchen committed almost 2 years ago
[4/N][torch.compile] clean up set_torch_compile_backend (#10401)
youkaichao committed almost 2 years ago
[Bugfix] Ignore ray reinit error when current platform is ROCm or XPU (#10375)
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed almost 2 years ago
[Misc] Add uninitialized params tracking for `AutoWeightsLoader` (#10327)
Isotr0py committed almost 2 years ago
[Misc] Enhance offline_inference to support user-configurable paramet… (#10392)
wchen61 committed almost 2 years ago
[Bugfix] Fix mrope_position_delta in non-last prefill chunk (#10403)
电脑星人 committed almost 2 years ago
[Hardware] [HPU]add `mark_step` for hpu (#10239)
Kunshang Ji committed almost 2 years ago
[platforms] refactor cpu code (#10402)
youkaichao committed almost 2 years ago
[Bugfix][CPU] Fix CPU embedding runner with tensor parallel (#10394)
Isotr0py committed almost 2 years ago
[CI/Build] Fix IDC hpu [Device not found] issue (#10384)
Chendi.Xue committed almost 2 years ago
[V1] Refactor model executable interface for all text-only language models (#10374)
Roger Wang committed almost 2 years ago
[2/N][torch.compile] make compilation cfg part of vllm cfg (#10383)
youkaichao committed almost 2 years ago
[V1] Add code owners for V1 (#10397)
Woosuk Kwon committed almost 2 years ago