public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src
History
Daniel Bevenius 3617008c37
ggml-cpu : fix padding in ggml_timestep_embedding (llama/15917) 
This commit fixes the zero padding for odd dimensions in
ggml_compute_forward_timestep_embedding_f32.
The motivation for this is that currently if an odd dimension is used,
the padding check incorrectly uses the dimension value for indexing.
For example, with dim=15:

Elements 0-6 are set to cosine values
Elements 7-13 are set to sine values
Element 14 is left uninitialized (contains garbage)
Element 15 is correctly set to zero

This fix changes embed_data[dim] to embed_data[2 * half] so that
element 14 (the first unused element) is properly set to zero as well
as the last element.

Resolves: https://github.com/ggml-org/ggml/issues/1324
 		2025-09-20 13:45:27 +03:00
..
ggml-amx ggml : adapt AMX to tensor->grad removal (llama/0) 2024-11-20 21:00:08 +02:00
ggml-blas vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-cann CANN: Add ROPE sin/cos cache for reuse (llama/15912) 2025-09-20 13:42:53 +03:00
ggml-cpu ggml-cpu : fix padding in ggml_timestep_embedding (llama/15917) 2025-09-20 13:45:27 +03:00
ggml-cuda HIP: use v_dot2_f32_f16 instruction for FA (llama/15884) 2025-09-20 13:42:52 +03:00
ggml-hip HIP: bump requirement to rocm 6.1 (llama/15296) 2025-08-18 20:30:45 +03:00
ggml-metal metal : make the backend async (llama/15906) 2025-09-20 13:44:27 +03:00
ggml-musa CUDA: replace GGML_CUDA_F16 with CUDA arch checks (llama/15433) 2025-09-20 13:42:38 +03:00
ggml-opencl vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-rpc vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-sycl vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-vulkan vulkan: throw the oom error instead of no memory type found (llama/15905) 2025-09-20 13:42:53 +03:00
ggml-webgpu vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-zdnn vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
CMakeLists.txt ggml: initial IBM zDNN backend (llama/14975) 2025-08-18 20:30:45 +03:00
ggml-alloc.c llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-backend-impl.h vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-backend-reg.cpp ggml: initial IBM zDNN backend (llama/14975) 2025-08-18 20:30:45 +03:00
ggml-backend.cpp vulkan: sort graph to allow more parallel execution (llama/15850) 2025-09-20 13:42:52 +03:00
ggml-common.h llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-impl.h llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-opt.cpp finetune: SGD optimizer, more CLI args (llama/13873) 2025-08-18 20:30:45 +03:00
ggml-quants.c ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (llama/15379) 2025-08-18 20:30:45 +03:00
ggml-quants.h llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-threading.cpp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
ggml-threading.h remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) 2024-12-18 12:52:16 +02:00
ggml.c cuda : fix supports_op condition for get_rows when number of blocks is too large (llama/15868) 2025-09-20 13:42:52 +03:00
ggml.cpp ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 2025-05-29 09:56:26 +03:00
gguf.cpp ggml : prevent integer overflow in gguf tensor size calculation (llama/14595) 2025-07-12 19:23:56 +03:00