vulkan: Implement topk_moe fused shader, ported from CUDA (#16641)

This is similar to the CUDA shader from #16130, but doesn't use shared memory
and handles different subgroup sizes.

CUDA: use registers instead of smem in topk-moe (#16647)

Uses the technique used in the vulkan PR #16641. Neat trick!

opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602)

* opencl: transposed gemm/gemv moe kernel with mxfp4,f32

* add restore kernel for moe transpose

* fix trailing whitespaces

* resolve compilation warnings

llama-model: fix insonsistent ctxs <-> bufs order (#16581)

rpc : report actual free memory (#16616)

* rpc : report actual free memory

Start reporting the free memory on every device instead of using
fixed values. Now llama-cli users can get a nice memory breakdown
when using RPC devices.

* drop --mem in rpc-server

vulkan: Add State Space Model (SSM) Operations Support (#16463)

* vulkan: implement SSM scan operation

Add State Space Model scan operation to the Vulkan backend.

Signed-off-by: Giuseppe Scrivano <[email protected]>

* vulkan: implement SSM conv operation

Add State Space Model conv operation to the Vulkan backend.

Signed-off-by: Giuseppe Scrivano <[email protected]>

---------

Signed-off-by: Giuseppe Scrivano <[email protected]>

ggml : fix SpaceMit IME array out-of-bounds in task assignment (#16629)

Fix incorrect task-to-batch index calculation in the quantization phase.

The bug caused out-of-bounds access to qnbitgemm_args array when
compute_idx exceeded per_gemm_block_count_m, leading to invalid
pointer dereferences and SIGBUS errors.

Correctly map tasks to batches by dividing compute_idx by
per_gemm_block_count_m instead of block_size_m.

Example:
  batch_feature=1, gemm_m=30, block_size_m=4
  per_gemm_block_count_m = 8, task_count = 8

  Old: gemm_idx = 4/4 = 1 (out of bounds  New: gemm_idx = 4/8 = 0 (correct)

Tested on SpaceMit K1 RISC-V64 with qwen2.5:0.5b model.

Co-authored-by: muggle <[email protected]>

vulkan: fix debug build (add_rms_len/data not found) (#16624)

metal : add `CONV_TRANSPOSE_2D` (#16542)

* initial: headers and metal-device.cpp updates

* adding conv_transpose_2d

* fix type

* fix type: int32->int64

* Update ggml/src/ggml-metal/ggml-metal.metal

Co-authored-by: Georgi Gerganov <[email protected]>

* Update ggml/src/ggml-metal/ggml-metal.metal

Co-authored-by: Georgi Gerganov <[email protected]>

* Update ggml/src/ggml-metal/ggml-metal.metal

Co-authored-by: Georgi Gerganov <[email protected]>

* add checks for src[0] and src[1]; add type checks

* Update ggml-metal.metal

Co-authored-by: Georgi Gerganov <[email protected]>

* add more tests, add optimization to threading

* add dynamic memory allocation in metal

---------

Co-authored-by: Georgi Gerganov <[email protected]>

grammar : use int64_t to avoid int overflows in int schema to grammar…