[Core] Async Scheduling X Spec Decoding Compatibility (#24799)

Ronald committed 12 months ago

[Bugfix] Fix GPT-OSS on AMD after #28603 (#28816)

Zhewen Li committed 12 months ago

Cast return value to int64_t for cache size (#28814)

tiehexue committed 12 months ago

[Bugfix][Perf] Revert applying HF processor on text-only inputs for multimodal models (#28858)

Roger Wang committed 12 months ago

[BugFix] Temporary fix for IMA with MTP = 2 and full-cg (#28315)

Lucas Wilkinson committed 12 months ago

[XPU] work around for sp, avoid custom op import error (#28822)

Kunshang Ji committed 12 months ago

[Metrics] Fix KV cache usage percent metric multiproc (#28792)

Jae-Won Chung committed 12 months ago

[BugFix] Fix glm4_moe_mtp load weights bug (#28805)

wuyaoxuehun committed 12 months ago

[CPU][Bugfix] Fix _to_list in CPU model runner (#28824)

Li, Jiang committed 12 months ago

[Doc] Add llama4 LoRA tag (#28825)

Jee Jee Li committed 12 months ago

[Bugfix][Model] Prevent special token leakage in KimiK2ToolParser streaming mode (#28543)

Jay Caldwell committed 12 months ago

[ROCm][Qwen3-32B] Fix AITER MHA accuracy issue cause by #25763 (#28670)

Xiake Sun committed 12 months ago

[NIXL][XPU] update install script of NIXL (#28778)

liuzhenwei committed 12 months ago

[Performance][Fix] update nvfp4 code to support renorm routing (#28569)

jiahanc committed 12 months ago

[BugFix] Fix async scheduling + chunked prefill + preemption (#28787)

Nick Hill committed 12 months ago

Feature: Support Relu2 in FusedMoE fp8 cutlass path (#27261)

amirkl94 committed 12 months ago

[Model][QwenVL] Optimize `Qwen2_5_VisionAttention` q,k preparation (#28769)

Lukas Geiger committed 12 months ago

fix comment typo (#28802)

Ning Xie committed 12 months ago

[Doc]: fix typos in various files (#28811)

Didier Durand committed 12 months ago

Fix gpt oss weight loading with EP + bf16 (#28765)

Anna Shors committed 12 months ago