models : remove redundant ggml_cont calls now supported by all unary kernels (#30198)
* models: remove redundant ggml_cont calls now supported by CUDA unary kernels * models: restore cont_2d after sigmoid for broadcast mul, clean dflash cont * Update src/models/qwen3next.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * models: restore cont_2d before sigmoid in qwen3next --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
1 parent
4413a19241
commit
071b553fb1
3 files changed
+1
-9
No files matched your search
@@ -337,7 +337,7 @@ static void build_dspark_markov_head(llm_graph_context & g, const llama_model &
|
||||
// bonus anchor slot: pass the logits through unbiased, pad the (unread) confidence column
|
||||
cat = ggml_cont(ctx0, ggml_view_2d(ctx0, base, n_vocab, n_blocks, base_stride, 0));
|
||||
if (has_conf) {
|
||||
cat_conf = ggml_sigmoid(ctx0, ggml_cont(ctx0, ggml_view_2d(ctx0, base, 1, n_blocks, base_stride, 0)));
|
||||
cat_conf = ggml_sigmoid(ctx0, ggml_view_2d(ctx0, base, 1, n_blocks, base_stride, 0));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user