Releases: ggml-org/llama.cpp
Releases · ggml-org/llama.cpp
b5797
b5795
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411) * [CANN]update to aclnnGroupedMatmulV2 Signed-off-by: noemotiovon <[email protected]> * Support MUL_MAT_ID on 310p Signed-off-by: noemotiovon <[email protected]> * fix editorconfig Signed-off-by: noemotiovon <[email protected]> --------- Signed-off-by: noemotiovon <[email protected]>
b5794
vulkan: Split large mul_mat_id to fit in shared memory (#14451)
b5793
add GELU_ERF (#14455)
b5792
ggml : remove trailing whitespace (#0)
b5788
opencl : add GEGLU, REGLU, SWIGLU (#14456)
b5787
Add Conv2d for CPU (#14388) * Conv2D: Add CPU version * Half decent * Tiled approach for F32 * remove file * Fix tests * Support F16 operations * add assert about size * Review: further formatting fixes, add assert and use CPU version of fp32->fp16
b5785
metal : disable fast-math for some cpy kernels (#14460) * metal : disable fast-math for some cpy kernels ggml-ci * cont : disable for q4_1 ggml-ci * cont : disable for iq4_nl ggml-ci
b5784
ggml-cpu: sycl: Re-enable exp f16 (#14462)
b5783
test-backend-ops : disable llama test (#14461)