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 12, 08:30 UTC
main
[compile] Include `enable_sleep_mode` into caching factors. (#29696)
Zhengxu Chen committed 12 months ago
bugfix: correct attn output with base 2 or e (#28840)
Augusto Yao committed 12 months ago
Revert "[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#28971)" (#29697)
Huamin Li committed 12 months ago
[Bugfix] fix dots.llm1.inst (#29687)
Jiangyun Zhu committed 12 months ago
[Misc] Remove redundant `ClassRegistry` (#29681)
Cyrus Leung committed 12 months ago
[CI/Build]: make it possible to build with a free-threaded interpreter (#29241)
Ralf Gommers committed 12 months ago
[Perf] Optimize EAGLE prepare_inputs_padded with triton kernels (#28597)
Benjamin Chislett committed 12 months ago
[Frontend] Remap -O to -cc commandline flag (#29557)
Yanan Cao committed 12 months ago
Remove `all_special_tokens_extended` from tokenizer code (#29686)
Harry Mellor committed 12 months ago
[Chore] Rename `Processor` to `InputProcessor` (#29682)
Cyrus Leung committed 12 months ago
[CI/Build] Rework CPU multimodal processor test (#29684)
Isotr0py committed 12 months ago
[Docs] Add CLI reference doc for `vllm bench sweep plot_pareto` (#29689)
Harry Mellor committed 12 months ago
[Chore]: Reorganize model repo operating functions in `transformers_utils` (#29680)
Isotr0py committed 12 months ago
[V0 deprecation] Clean up legacy paged attention helper functions (#28043)
Isotr0py committed 12 months ago
[Doc]: fixing typos in multiple files. (#29685)
Didier Durand committed 12 months ago
add add_truncate_prompt_tokens in repr for PoolingParams (#29683)
果冻虾仁 committed 12 months ago
[mypy] Enable type checking for more directories (#29674)
Cyrus Leung committed 12 months ago
Guard FlashInfer sampler using the same check as FlashInfer attention backend (#29415)
Harry Mellor committed 12 months ago
[Misc] Remove `yapf` directives (#29675)
Cyrus Leung committed 12 months ago
Remove upstream fa checks (#29471)
Mingyuan Ma committed 12 months ago