llama.cpp
models: remove redundant ggml_cont calls now supported by CUDA unary kernels
#30198
Merged
Overview
Commits
4
Changes
View On GitHub

models: remove redundant ggml_cont calls now supported by CUDA unary kernels #30198

CISC merged 4 commits into ggml-org:master from saady789:cuda-remove-qwen-cont
saady789
saady789 models: remove redundant ggml_cont calls now supported by CUDA unary …
3b75c63c
saady789 saady789 requested a review from CISC CISC 23 days ago
github-actions github-actions added model
CISC
CISC approved these changes on 2026-10-09
CISC
CISC
saady789 models: restore cont_2d after sigmoid for broadcast mul, clean dflash…
28d46f2a
saady789
CISC
CISC commented on 2026-10-10
saady789 Update src/models/qwen3next.cpp
8199de91
saady789 models: restore cont_2d before sigmoid in qwen3next
5f63a2fc
CISC CISC merged 071b553f into master 19 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
model
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum