[release] Minor fixes to release annotation and wheel upload (#33129)

Kevin H. Luu committed 9 months ago

Add Triton fused MoE config for B200 (Nemotron Nano) (#32804)

danisereb committed 9 months ago

[Bugfix][Kernel] Fix negative memory offset in GDN Triton kernel (#33326)

CarstyYou committed 9 months ago

[NVIDIA] [feat] Integrate flashinfer Trtllmgen bf16 moe (#32954)

Linda committed 9 months ago

[BUGFIX][XPU] fix memory check after XPU reuse GPU_worker (#33358)

Chendi.Xue committed 9 months ago

[Chore] Move `MediaConnector` to `vllm.multimodal.media` (#33324)

Cyrus Leung committed 9 months ago

[ez] Delete torch25_custom_graph_pass (#33287)

Angela Yi committed 9 months ago

[Bugfix] Fix broken GLM-OCR initialization (#33350)

Isotr0py committed 9 months ago

[Multimodal] Simplify MM input definitions (#33331)

Cyrus Leung committed 9 months ago

[Backport] [Kimi-K2.5] Replace torch.cuda with current_platform for d… (#33320)

sthWrong committed 9 months ago

[Intel GPU] refine xpu worker (#32894)

Kunshang Ji committed 9 months ago

[Models] Qwen3-ASR (#33312)

Roger Wang committed 9 months ago

[Bugfix][CPU] Fix thread num for shared memory communication (#33317)

Li, Jiang committed 9 months ago

[Voxtral] Streaming example (#33042)

Patrick von Platen committed 9 months ago

[Quantization][Refactor] use platform dict to choose kernel (#33130)

zofia committed 9 months ago

[Bug Fix] Handle variable-length tensors in MultiModalFlatField batching (#31751)

andrii.pasternak committed 9 months ago

[BugFix] Async Eplb fix potential race condition (#32881)

Ilya Markov committed 9 months ago

[fix] tesdt mcp_tool_calling_streaming with a more complex math question (#32769)

daniel-salib committed 9 months ago

[Chore] Remove `use_data_parallel` kwargs from ViT implementation (#33310)

Isotr0py committed 9 months ago

[Misc] Cleanup Kimi-K2.5's vision chunk modality entrypoints (#33157)

Isotr0py committed 9 months ago