main
[Infer] Revise and Adapt Triton Kernels for Spec-Dec (#5401)
[kernel] Support New KCache Layout - Triton Kernel (#5677)
[NFC] Fix code factors on inference triton kernels (#5743)
[Inference]Fused the gate and up proj in mlp，and optimized the autograd process. (#5365)
[devops] remove post commit ci (#5566)
[misc] update pre-commit and run all files (#4752)
[fix] multi graphs capture error