Jeff Bolz f407c5e562 vulkan/cuda: fix topk_moe with exp_probs_b (llama/18071) ... I updated test_topk_moe to more closely match llm_graph_context::build_moe_ffn and added coverage for exp_probs_b and some other missing combinations. This exposed a bug in both CUDA and Vulkan backends where they were assuming the input to argsort and the input to get_rows are the same. I'd like to optimize this graph in another change, but for now just get it functional. CUDA also had a bug where it got n_experts from the wrong place, leading to GGML_ASSERT failures in some of the new tests.		2025-12-31 17:52:09 +02:00
..
cmake	ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094)	2025-08-18 20:30:45 +03:00
include	llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (llama/16653)	2025-12-18 08:20:56 +02:00
src	vulkan/cuda: fix topk_moe with exp_probs_b (llama/18071)	2025-12-31 17:52:09 +02:00
.gitignore	whisper : reorganize source code + improve CMake (#2256)	2024-06-26 19:34:09 +03:00
CMakeLists.txt	ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (llama/17977)	2025-12-31 17:52:09 +02:00