[Doc] Add max_lora_rank configuration guide (#22782)

633WHU committed over 1 year ago

[Bugfix] Fix Nemotron VL image processing (#22739)

Duc-Viet Hoang committed over 1 year ago

[Model] Add missing prefix to glm4_1v (#22716)

Yuxuan Zhang committed over 1 year ago

[Model] Add option to run Step3VisionEncoder in DP (#22697)

zzh142857 committed over 1 year ago

[gpt-oss] upgrade gpt-oss to v0.0.3 and add version check (#22768)

Chen Zhang committed over 1 year ago

[Perf] Support topk softmax fused kernel for broader num_experts (#22211)

shixianc committed over 1 year ago

[Bug] Fix Unexpected Keyword Argument 'w1_bias' (#22757)

Wentao Ye committed over 1 year ago

Remove unneeded ROCm platform import when using CUDA (#22765)

Michael Goin committed over 1 year ago

Force TRTLLM attention for gpt-oss on SM100 (#22678)

Michael Goin committed over 1 year ago

[Bugfix] Fix default enable for CUTLASS MLA on SM100 (#22738)

Michael Goin committed over 1 year ago

Fix cuda illegal mem access with Llama4 TP8 + rms_norm custom op (#22701)

Po-Han Huang (NVIDIA) committed over 1 year ago

[V0 Deprecation] Remove args for multi-step scheduling (#22779)

Woosuk Kwon committed over 1 year ago

[Misc] Remove tests/multi_step/__init__.py (#22778)

Woosuk Kwon committed over 1 year ago

[V0 Deprecation] Remove multi-step scheduling (#22138)

Woosuk Kwon committed over 1 year ago

Add hardware plugins to installation doc (#22732)

Michael Goin committed over 1 year ago

[Model] Decouple glm4v (#22751)

Jee Jee Li committed over 1 year ago

Fix Transformers backend tensor parallel for multimodal models (#22673)

Harry Mellor committed over 1 year ago

[Docs] Hide the navigation and toc sidebars on home page (#22749)

Harry Mellor committed over 1 year ago

[Bugfix] Bump DeepGEMM Version to Fix SMXX Layout Issues (#22606)

Frank Wang committed over 1 year ago

[Misc] parametrize 'dtype' in test_flash_mla (#22641)

RUTHLESS-BOT committed over 1 year ago