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 14, 05:30 UTC
main
[New Model] Support Command-A-Vision (#22660)
dongluw committed over 1 year ago
[DOC] update v1_guide with INTEL HW (#22679)
Chendi.Xue committed over 1 year ago
Move `SchedulerConfig` from `config/__init__.py` to `config/scheduler.py` (#22626)
Harry Mellor committed over 1 year ago
[Bugfix] Fix ModernBert load & Enable sliding window attention for bidirectional attention. (#22637)
wang.yuqi committed over 1 year ago
[doc] Update x86 CPU-inference installation doc to reflect optionality of AVX512f (#22707)
Sooraj S committed over 1 year ago
[Doc] Added unmentioned required option "method" in the usage of EAGLE-3 based models (#21737)
Hongsheng Liu committed over 1 year ago
Fix passing `SpeculativeConfig` from the CLI (#22652)
Harry Mellor committed over 1 year ago
[gpt-oss] Small bug fixes for frontend (#22512)
Chen Zhang committed over 1 year ago
[gpt-oss] Fix mxfp4 support (#22700)
Chen Zhang committed over 1 year ago
Migrate MiniCPMVImageInputs to TensorSchema (#21939)
Benji Beck committed over 1 year ago
[CI] Increase timeout for test_completion_with_image_embeds (#22670)
Michael Goin committed over 1 year ago
[CI Failure] Use float32 for tests/entrypoints/openai/test_audio.py (#22686)
Michael Goin committed over 1 year ago
Upgrade FlashInfer to v0.2.11 (#22613)
Po-Han Huang (NVIDIA) committed over 1 year ago
Re-enable Xet on TPU tests now that `hf_xet` has been updated (#22666)
Harry Mellor committed over 1 year ago
Enable 4bit bnb prequant MOE (#21548)
Andy Chen committed over 1 year ago
[gpt-oss] Add test for response API + harmony (but skipped) (#22554)
Chen Zhang committed over 1 year ago
[gpt-oss] Support streaming in response API (#22431)
Chen Zhang committed over 1 year ago
Support more parallel styles in Transformers backend TP (#22651)
Harry Mellor committed over 1 year ago
[CI] Skip Tree Attn Test in `test_max_len.py` to unblock CI (#22664)
TJian committed over 1 year ago
[BugFix] [Spec Decode] Remove LlamaForCausalLMEagle3 to fix CI (#22611)
22quinn committed over 1 year ago