whisper.cpp/ggml/include
Gaurav Garg 1a1900f90c Remove padding and multiple D2D copies for MTP (llama/24086)
* Make ggml_gated_delta_net take only the initial recurrent state (D, 1, n_seqs) and passes the snapshot count K as an op parameter instead of inferring it from state->ne[1].

Remove the padding hack and copy all emitted snapshots into the recurrent cache with a single strided ggml_cpy

* Make GDN changes in all backends. Address review comments.

* Fix CI build errors
2026-06-15 10:33:53 +03:00
..
ggml-alloc.h TP: fix entirely zero-sized slices per device (llama/23525) 2026-05-25 12:26:07 +03:00
ggml-backend.h TP: quantized KV cache support (llama/23792) 2026-06-08 14:36:36 +03:00
ggml-blas.h
ggml-cann.h
ggml-cpp.h
ggml-cpu.h
ggml-cuda.h
ggml-hexagon.h
ggml-metal.h
ggml-opencl.h
ggml-openvino.h
ggml-opt.h
ggml-rpc.h ggml : add GGML_OP_COL2IM_1D (llama/24206) 2026-06-15 10:33:53 +03:00
ggml-sycl.h
ggml-virtgpu.h
ggml-vulkan.h
ggml-webgpu.h
ggml-zdnn.h
ggml-zendnn.h
ggml.h Remove padding and multiple D2D copies for MTP (llama/24086) 2026-06-15 10:33:53 +03:00
gguf.h ggml: `gguf_init_from_callback` and `gguf_init_from_buffer` (llama/22341) 2026-05-25 12:44:04 +03:00