]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: refactor topk-moe to enable more models (GLM 4.7, Nemotron etc.) (llama/19126)
authorAman Gupta <redacted>
Thu, 29 Jan 2026 02:31:28 +0000 (10:31 +0800)
committerGeorgi Gerganov <redacted>
Fri, 30 Jan 2026 11:49:29 +0000 (13:49 +0200)
commit7e027464c07a678f9aa49eb1ae0191f93c9089c5
treeb797e492982faa11ab6f29545b7d0adb3cab312a
parentbc269379cba9088a92cb6b7985b4c67e0199eb2f
CUDA: refactor topk-moe to enable more models (GLM 4.7, Nemotron etc.) (llama/19126)
src/ggml-cuda/ggml-cuda.cu
src/ggml-cuda/topk-moe.cu
src/ggml-cuda/topk-moe.cuh