[Bugfix] Use the correct repository revision for secondary artifact loaders (#57461)

Clinton Thomas committed 23 days ago

[Bugfix][Logging] Preserve application log record factories (#58747)

Misha Goin committed 24 days ago

[Multimodal] Avoid extra d2d for encoder cudagraph with fused input norm (#56711)

Isotr0py committed 24 days ago

[ROCm][Refactor] Move DeepSeek-V4/V4.1 multi-stream overlap gate to ROCm platform (#58983)

Shanshan Shen committed 24 days ago

[Perf][Qwen3.8] Reduce PLE metadata construction overhead (#58114)

Jiangyun Zhu committed 24 days ago

[Bugfix][Spec Decode] Implement get_top_tokens() on the ROCm DeepSeek V4 MTP drafter (#57568)

BaoYunkai committed 24 days ago

[Bugfix][Model] Gemma4: register aliased embedding scalars as buffers (#54213)

Yannick Schnider committed 24 days ago

[Perf][Qwen4Exp] Fuse HC down projection and SiLU on NVIDIA (#58957)

Thien Tran committed 24 days ago

Revert "[CI] Shard (H200 MIG 35GB / MI355 DPX) Entrypoints Integration (Pooling) into named jobs (#58652)" (#59011)

Kevin H. Luu committed 24 days ago

[CPU] Include vLLM Recipes tooling in release image to deploy models using vLLM Recipes (#58796)

Louie Tsai committed 24 days ago

[Bugfix][Qwen4Exp] Release the profiling KV cache held by QSA key views (#58961)

Gabriel Wu committed 24 days ago

[CI] Split Dynamic Shapes out of (H200 MIG 35GB) PyTorch Compilation + (MI300) mirror (#58451)

Thang Nguyen committed 24 days ago

[CI] Shard (H200 MIG 35GB / MI355 DPX) Entrypoints Integration (Pooling) into named jobs (#58652)

Thang Nguyen committed 24 days ago

[Misc] Name each backend and its kernel block sizes in block-size errors (#58557)

Eugenio "Jay" Zuccarelli committed 24 days ago

[Skills] Update kernel-microbenchmark to include ROCm (#58646)

Thien Tran committed 24 days ago

[CPU] Add video inferencing via torchcodec on s390x (#58693)

Rehan Khan committed 24 days ago

[CPU] Use accelerator memory API in DiffusionGemma (#58964)

zhao, zhenhui committed 24 days ago

[CI] Allowlist-shrink batch 1: wire 17 root-level tests + drop 5 stale watermarking entries into misc.yaml (#58055)

Turner Jabbour committed 24 days ago

[Benchmark] Add Responses API backend to vllm bench serve (#54628)

Harshil committed 24 days ago

[Bugfix] Fix the two multimodal root tests that fail on main (OpenPangu-VL embed merge, MiMo sink test fixture) (#58900)

Kevin H. Luu committed 24 days ago