llama.cpp/ggml/src/ggml-opencl
Johannes Gäßler 39b96f8fe1 ggml: backend-agnostic tensor parallelism 2026-02-05 21:49:34 +01:00
..
kernels opencl: refactor some ops, concat, repeat, tanh and scale (#19226) 2026-02-02 15:54:43 -08:00
CMakeLists.txt opencl: add optimized q8_0 mm kernel for adreno (#18871) 2026-01-30 10:19:27 -08:00
ggml-opencl.cpp ggml: backend-agnostic tensor parallelism 2026-02-05 21:49:34 +01:00