b6782

mtmd : support home-cooked Mistral Small Omni (#14928)

b6665

HIP: add IMbackK to codeowner (#16375)

b6503

CANN: Remove print (#16044)

Signed-off-by: noemotiovon <757486878@qq.com>

b6153

perplexity: give more information about constraints on failure (#15303)

* perplexity: give more information about constraints on failure

This checks whether -np is insufficient vs context, and provides clues as to how much is needed for each.

* log formatting

* log error and return instead of storing max_seq_exceeded int

* check if s0 is zero for -np check

b6140

HIP: disable sync warp shuffel operators from clr amd_warp_sync_funct…

b6106

ggml: Add basic SET_ROWS support in WebGPU (#15137)

* Begin work on set_rows

* Work on set rows

* Add error buffers for reporting unsupported SET_ROWS indices

* Remove extra comments

b6039

opencl: add `mul_mat_f32_f32_l4_lm` and `mul_mat_f16_f32_l4_lm` (#14809)

b6020

CUDA: add roll (#14919)

* CUDA: add roll

* Make everything const, use __restrict__

b5926

convert : fix Ernie4.5 MoE without shared experts (#14746)

b5581

opencl: add `backend_synchronize` (#13939)

* This is not needed by the normal use where the result is read
  using `tensor_get`, but it allows perf mode of `test-backend-ops`
  to properly measure performance.