qwen4exp : build the QSA selection without the kq_mask (#30965)
* qwen4exp : build the QSA selection without the kq_mask * clean * lang * qwen4exp : reshape the fused QSA selection to the kq_mask streams ggml_top_k_mask with a single keep row returns [n_kv, n_tokens], while build_attn_qsa expects the kq_mask layout [n_kv, n_tokens/n_stream, 1, n_stream]. With several streams the shape assert failed at graph reserve. * test the QSA optimization * reword * update build_fused_top_k_mask instead of handwiring * simplify * keep il at the end for consistency
This commit is contained in:
1 parent
da2ee1e7a6
commit
5c31142682
6 files changed
+28
-14
No files matched your search
@@ -975,7 +975,7 @@ ggml_tensor * llama_model_glm5_next::graph::build_kpool_select(
|
||||
ggml_tensor * tail = hparams.indexer_kpool_select_tail ? inp_kpool->tail_idxs : nullptr;
|
||||
GGML_ASSERT(kpool*n_top_pool + (tail ? tail->ne[0] : 0) == (int64_t) inp_kpool->n_sel);
|
||||
|
||||
ggml_tensor * sel = build_fused_top_k_mask(kq_mask, top_k, score, inp_kpool->pool_idxs, tail, il);
|
||||
ggml_tensor * sel = build_fused_top_k_mask(kq_mask, top_k, score, inp_kpool->pool_idxs, tail, nullptr, il);
|
||||
cb(sel, "indexer_sel", il);
|
||||
|
||||
return sel;
|
||||
|
||||
Reference in new issue
Block a user