[torch.compile] Stop compiling identical artifacts (#34003)

Richard Zou committed 9 months ago

[Kernel] Add KernelConfig flag to enable/disable FlashInfer autotune (#34006)

Mohammad Miadh Angkad committed 9 months ago

[Renderer] Define `render_cmpl` and `render_chat` (#34039)

Cyrus Leung committed 9 months ago

[CI][Build] Pin grpcio-tools==1.78.0 (#34048)

wang.yuqi committed 9 months ago

[Misc] Simplify `get_max_tokens` (#34036)

Cyrus Leung committed 9 months ago

Fix spelling errors (#33978)

lukec committed 9 months ago

[ROCm][CI] Pinning lm-eval version to resolve multi-modal small eval bug (#34038)

Andreas Karatzas committed 9 months ago

[Misc] Make `PlaceholderRange.get_num_embeds` a method (#34035)

Cyrus Leung committed 9 months ago

[Kernel] Add enable_sm120_or_later for SM121 (DGX Spark) CUTLASS support (#33517)

Vel committed 9 months ago

[Revert] Add util `handle_deprecated` back (#33998)

Wentao Ye committed 9 months ago

fix description in plugin_system.md (#33999)

果冻虾仁 committed 9 months ago

[ModelRunner V2] Revert token rank comparison difference for now (#34017)

Nick Hill committed 9 months ago

[Misc] Add backward-compatible import aliases for renamed translations module (#34015)

kourosh hakhamaneshi committed 9 months ago

[Bugfix] Fix _fused_moe_lora_expand signature mismatch (#33821)

Xin Yang committed 9 months ago

[CI][AMD]Bugfix] Check that model_config is not None in enable_norm_pad_fusion (#34007)

rasmith committed 9 months ago

[Bugfix] Fix Whisper tokenization (#34011)

Nicolò Lucchesi committed 9 months ago

[Bugfix] Fix QK Norm+RoPE fusion pattern matching on B200+FP8 (#33967)

Ikenna committed 9 months ago

[Feat][RL] Pause and Resume with keep requests for single engine (#32351)

Aaron Hao committed 9 months ago

[bugfix] [ROCm] Fix premature CUDA initialization in platform detection (#33941)

kourosh hakhamaneshi committed 9 months ago

Fix RoutingMethodType logic (#33919)

Dimitrios Bariamis committed 9 months ago