[compile] Reduce log spam from compile. (#36044)

Zhengxu Chen committed 8 months ago

[Model Runner V2] Misc code simplification (#35941)

Nick Hill committed 8 months ago

[ROCm][CI] Added MI325 mirrors (stage C) (#35239)

Andreas Karatzas committed 8 months ago

[Misc] Support OOT linear method registering (#35981)

Shanshan Shen committed 8 months ago

[Bugfix] Fix passing of activation_type to trtllm fused MoE NVFP4 and FP8 (#36017)

amitz-nv committed 8 months ago

[RL] [Weight Sync] Guard IPC update-info pickle deserialization behind insecure serialization flag (#35928)

Simon Mo committed 8 months ago

[Bugfix] Fix race in non-blocking num_accepted_tokens GPU->CPU copy (#36013)

Thomas Parnell committed 8 months ago

[CI] Bump `mypy` version (#34950)

Harry Mellor committed 8 months ago

Add PyTorch profiler schedule support with warmup/active iterations (#35240)

fenypatel99 committed 8 months ago

[Docs] Document security risks of GPT-OSS Python tool (#35139)

Russell Bryant committed 8 months ago

[UX] Remove NoOpOffloader log (#35678)

Robert Shaw committed 8 months ago

[torch.compile] Stop lazily compiling (#35472)

Richard Zou committed 8 months ago

[Docs] Clarify structured outputs configuration for Qwen3 reasoning mode (#32441)

Davina Zaman committed 8 months ago

[CI] Add Blackwell AsyncTP correctness test (#35871)

Stefano Castagnetta committed 8 months ago

[Model Runner V2] Fix pooling (#36019)

Nick Hill committed 8 months ago

[Kernel][Mamba] Optimize Mamba2 SSD prefill Triton kernels (#35397)

tomeras91 committed 8 months ago

[Frontend] Add vllm launch command for GPU-less preprocessing serving (#34551)

Hyunkyun Moon committed 8 months ago

docs: update CPU Docker images to reference Docker Hub instead of AWS ECR (#34882)

Maxime Grenu committed 8 months ago

docs: add version requirement note for --profiler-config flag (#32454)

Abhishek Mathukiya committed 8 months ago

[Docs] Add RunPod GPU deployment guide for vLLM (#34531)

Chen committed 8 months ago