Ruben Ortlam ba36235565 vulkan: use flops instead of weight tensor size for submission heuristic (llama/25005) ...

* vulkan: extract flops calculation into function

* use flops instead of matmul src0 tensor size for submission threshold

* use unsigned ints

2026-07-10 13:06:42 +03:00

..

ggml-blas

…

ggml-cann

…

ggml-cpu

ggml-cpu: fix SVE leftover path in ggml_vec_dot_f32 (llama/24699)

2026-06-26 16:03:57 +03:00

ggml-cuda

Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy (llama/25057)

2026-07-10 13:06:42 +03:00

ggml-hexagon

hexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled weight repack, kernel-params, cached graphs (llama/24954)

2026-06-26 16:03:57 +03:00

ggml-hip

…

ggml-metal

metal : check for BF16 support in concat kernel (llama/24747)

2026-06-19 12:53:43 +03:00

ggml-musa

…

ggml-opencl

opencl: flash attention improvement (llama/25069)

2026-07-10 13:06:42 +03:00

ggml-openvino

Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy (llama/25057)

2026-07-10 13:06:42 +03:00

ggml-rpc

…

ggml-sycl

sycl : fix failed ut cases of norm (llama/25044)

2026-07-10 13:06:42 +03:00

ggml-virtgpu

…

ggml-vulkan

vulkan: use flops instead of weight tensor size for submission heuristic (llama/25005)

2026-07-10 13:06:42 +03:00

ggml-webgpu

vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU/NORM (llama/24582)

2026-06-26 16:03:57 +03:00

ggml-zdnn

…

ggml-zendnn

ggml-zendnn : fixed naming of matmul function (llama/20964)

2026-05-29 09:47:30 +03:00

CMakeLists.txt

ggml-cpu: Conditionally enable power11 backend based on compiler support (llama/24687)

2026-06-19 12:53:43 +03:00

ggml-alloc.c

…

ggml-backend-dl.cpp

…

ggml-backend-dl.h

…

ggml-backend-impl.h

…

ggml-backend-meta.cpp

Remove padding and multiple D2D copies for MTP (llama/24086)

2026-06-15 10:33:53 +03:00

ggml-backend-reg.cpp

…

ggml-backend.cpp

sched : reintroduce less synchronizations during split compute (llama/20793)

2026-07-10 13:06:42 +03:00

ggml-common.h

…

ggml-impl.h

…

ggml-opt.cpp

…

ggml-quants.c

…

ggml-quants.h

…

ggml-threading.cpp

…

ggml-threading.h

…

ggml.c

mtmd, arg: fix utf8 handling on windows (llama/24779)

2026-06-26 16:03:57 +03:00

ggml.cpp

…

gguf.cpp

ggml: gguf_init_from_callback and gguf_init_from_buffer (llama/22341)

2026-05-25 12:44:04 +03:00