llama : drop the redundant cnv from llm_attn_mask (#31558)
The dspark block mask is now derived at input-fill time: llm_attn_mask::block_uniform fills every token of a sequence with the mask row of its first token, so the graph-level reshape/repeat in dflash is gone and cnv always aliases raw. Assisted-by: dsh:llama.cpp/ggml-org/GLM-5.3-Flash-GGUF (Mac Studio, M5 Ultra, 256GB)
This commit is contained in:
1 parent
0f663d2471
commit
ca8daad199
14 files changed
+46
-69
No files matched your search
@@ -352,8 +352,6 @@ llm_graph_input_attn_no_cache * llama_model_clef::graph::build_attn_inp_causal()
|
||||
ggml_set_input(inp->self_attn_mask.raw);
|
||||
cb(inp->self_attn_mask.raw, "self_kq_mask", -1);
|
||||
|
||||
inp->self_attn_mask.cnv = inp->self_attn_mask.raw;
|
||||
|
||||
return (llm_graph_input_attn_no_cache *) res->add_input(std::move(inp));
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user