b1f65a4a7e
* vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron Also handle GGML_OP_SCALE at the end (nemotron, deepseek2). Fewer pipeline variants and spec constants, just use push constants. In test_topk_moe, change exp_probs_b to be 1D, matching real networks. Update test-backend-ops and ggml-backend to allow verifying multiple outputs in a fusion test (topk_moe has two outputs). Previously only the final node was verified. * change test_topk_moe to allow results in arbitrary order * disable sigmoid fusion for moltenvk |
||
|---|---|---|
| .. | ||
| ggml-alloc.h | ||
| ggml-backend.h | ||
| ggml-blas.h | ||
| ggml-cann.h | ||
| ggml-cpp.h | ||
| ggml-cpu.h | ||
| ggml-cuda.h | ||
| ggml-hexagon.h | ||
| ggml-metal.h | ||
| ggml-opencl.h | ||
| ggml-opt.h | ||
| ggml-rpc.h | ||
| ggml-sycl.h | ||
| ggml-vulkan.h | ||
| ggml-webgpu.h | ||
| ggml-zdnn.h | ||
| ggml-zendnn.h | ||
| ggml.h | ||
| gguf.h | ||