Add nightly b200 test for spec decode eagle correctness (#38577)

Rishi Puri committed 7 months ago

[ASR] Fix spacing bw chunks in multi chunk audio transcription (#39116)

Ekagra Ranjan committed 7 months ago

[XPU] check is_xccl_available before oneccl warmup (#39302)

Xinyu Chen committed 7 months ago

[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (#39129)

Michael Goin committed 7 months ago

[CI/Build] Update auto-rebase rule (#39429)

Cyrus Leung committed 7 months ago

[ROCm] Correctly guard fused_silu_mul_block_quant on ROCm (#39387)

Micah Williamson committed 7 months ago

[Quantization] Support Quark W8A8 INT8 MoE inference (#36320)

PikaPikachu committed 7 months ago

[Model Runner V2] Fix flex attention kv blocks calculation issue (#39353)

Wentao Ye committed 7 months ago

[ROCm][CI] Resolved nvidia package deps issue (#39421)

Andreas Karatzas committed 7 months ago

[Performance Improvement] Update `batched_count_greater_than` to handle batch size 1 without recompile (#38933)

Lucas Kabela committed 7 months ago

[CI/Build] Fix memory cleanup in MM test (#39411)

Cyrus Leung committed 7 months ago

[UX] Improve error message for MM input too long (#39409)

Cyrus Leung committed 7 months ago

[BugFix] fix tests/kernels/moe/test_moe_layer.py (#39404)

Richard Zou committed 7 months ago

[Tests] Add Qwen3-VL multimodal memory leak check (#39268)

lalit10 committed 7 months ago

nemotron-nano-vl: Allow `use_audio_in_video` to be passed at `vllm serve` time (#38538)

Andrii Skliar committed 7 months ago

[Core] Simplify API server handshake (#39364)

Nick Hill committed 7 months ago

[Docs] Bring README updates into docs README (#39397)

Harry Mellor committed 7 months ago

[Frontend][4/n] Improve pooling entrypoints | pooling. (#39153)

wang.yuqi committed 7 months ago

[CI] fix possible user permission issues in nightly index generation (#39390)

Shengqi Chen committed 7 months ago

Fix NUMA binding on non-CDMM Grace-Blackwell systems (#39361)

Qidong Su committed 7 months ago