llama.cpp/ggml
Jeff Bolz 863d341eeb
vulkan: perf_logger improvements (#15246)
* vulkan: perf_logger improvements

- Account for batch dimension in flops calculation.
- Fix how "_VEC" is detected for mat_mul_id.
- Fix "n" dimension for mat_mul_id (in case of broadcasting).
- Include a->type in name.

* use <=mul_mat_vec_max_cols rather than ==1
2025-08-14 08:38:10 -05:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include finetune: SGD optimizer, more CLI args (#13873) 2025-08-14 12:03:57 +02:00
src vulkan: perf_logger improvements (#15246) 2025-08-14 08:38:10 -05:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt HIP: add cmake option to enable compiler output of kernel resource usage metrics (#15103) 2025-08-07 16:44:14 +02:00