llama.cpp/ggml/src/ggml-vulkan
Jeff Bolz be47fb9285
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron (#18295)
* 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
2026-01-01 08:58:27 +01:00
..
cmake cmake: fix ggml-shaders-gen compiler paths containing spaces (#12747) 2025-04-04 10:12:40 -03:00
vulkan-shaders vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron (#18295) 2026-01-01 08:58:27 +01:00
CMakeLists.txt vulkan: Improve build time for MSVC (#16545) 2025-10-14 14:51:36 +02:00
ggml-vulkan.cpp vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron (#18295) 2026-01-01 08:58:27 +01:00