models : optimize qwen3next graph (#19375)

* models : optimizing qwen3next graph * cont * wip * wip * wip * wip * wip * wip * wip * wip * wip * wip * cont : remove redundant q, g chunking * minor * minor * avoid passing masks around * avoid concats during chunking * naming + shapes * update names and use prefix to disable CUDA graphs
2026-02-14 12:57:36 +02:00
parent b7742cf321
commit 1725e316c1
4 changed files with 263 additions and 300 deletions
@@ -489,9 +489,6 @@ private:
    ggml_tensor * build_layer_attn_linear(
         llm_graph_input_rs * inp,
                ggml_tensor * cur,
-                ggml_tensor * causal_mask,
-                ggml_tensor * identity,
-                ggml_tensor * diag_mask,
                        int   il);

    ggml_tensor * build_layer_ffn(
@@ -506,9 +503,6 @@ private:
                ggml_tensor * g,
                ggml_tensor * beta,
                ggml_tensor * state,
-                ggml_tensor * causal_mask,
-                ggml_tensor * identity,
-                ggml_tensor * diag_mask,
                        int   il);

    // returns pair of output and new state