llama.cpp
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron
#18295
Merged

vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron #18295

jeffbolznv
jeffbolznv jeffbolznv requested a review from ggerganov ggerganov 62 days ago
jeffbolznv jeffbolznv requested a review from 0cc4m 0cc4m 62 days ago
github-actions github-actions added testing
github-actions github-actions added Vulkan
github-actions github-actions added ggml
ggerganov
ggerganov approved these changes on 2025-12-22
0cc4m
0cc4m approved these changes on 2025-12-26
0cc4m
jeffbolznv vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron
bf21b783
jeffbolznv jeffbolznv force pushed from 4a174025 to 75bcc845 58 days ago
jeffbolznv
jeffbolznv change test_topk_moe to allow results in arbitrary order
797b4efa
jeffbolznv jeffbolznv force pushed from 75bcc845 to 797b4efa 58 days ago
jeffbolznv jeffbolznv force pushed from bfbd40e9 to 03b18c9e 58 days ago
jeffbolznv disable sigmoid fusion for moltenvk
86df5637
jeffbolznv jeffbolznv force pushed from 03b18c9e to 86df5637 58 days ago
jeffbolznv
0cc4m 0cc4m merged be47fb92 into master 53 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone