models : consolidate nextn row cropping into shared helpers (#30017)
* mimo2 : always emit h_nextn the other nextn-capable models set it unconditionally Assisted-by: pi:llama.cpp/MiMo-V2.6-Flash-MOPD * models : consolidate nextn row cropping into shared helpers - replace the duplicated crop conditions and the per-model flags (narrow_early, crop_before_ffn, crop_last_layer, emit_h_nextn) with two helpers on llm_graph_context: crop_before_nextn() / crop_after_nextn() - models that only tested embeddings_nextn_masked now share the same condition, so they crop the last layer before the nextn capture whenever extraction is off - t_h_nextn is now set unconditionally in mimo2, qwen4exp and deepseek4 (as in the other nextn-capable models); host-side reads stay gated by cparams.embeddings_nextn Assisted-by: pi:llama.cpp/MiMo-V2.6-Flash-MOPD
This commit is contained in:
1 parent
d7a695ef67
commit
f0c41e0168
20 files changed
+59
-62
No files matched your search
@@ -470,7 +470,7 @@ llama_model_qwen4exp::graph::graph(const llama_model & model, const llm_graph_pa
|
||||
cur = build_layer_attn(inp->get_attn(), mctx_hyb, inp_kpool, cur, inp_pos, sections, il);
|
||||
}
|
||||
|
||||
if (il == n_layer - 1 && inp_out_ids && (!cparams.embeddings_nextn || cparams.embeddings_nextn_masked)) {
|
||||
if (il == n_layer - 1 && crop_before_nextn(inp_out_ids)) {
|
||||
// everything below is per token, so drop the rows that produce no output
|
||||
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
|
||||
inject = ggml_get_rows(ctx0, inject, inp_out_ids);
|
||||
@@ -499,13 +499,11 @@ llama_model_qwen4exp::graph::graph(const llama_model & model, const llm_graph_pa
|
||||
}
|
||||
|
||||
// the MTP head reads the hc-wide residual, before the final mixer
|
||||
if (cparams.embeddings_nextn) {
|
||||
res->t_h_nextn = ggml_reshape_2d(ctx0, res_hc, n_embd*hc, res_hc->ne[2]);
|
||||
cb(res->t_h_nextn, "h_nextn", -1);
|
||||
ggml_build_forward_expand(gf, res->t_h_nextn);
|
||||
}
|
||||
res->t_h_nextn = ggml_reshape_2d(ctx0, res_hc, n_embd*hc, res_hc->ne[2]);
|
||||
cb(res->t_h_nextn, "h_nextn", -1);
|
||||
ggml_build_forward_expand(gf, res->t_h_nextn);
|
||||
|
||||
if (cparams.embeddings_nextn && !cparams.embeddings_nextn_masked && inp_out_ids) {
|
||||
if (crop_after_nextn(inp_out_ids)) {
|
||||
res_hc = ggml_reshape_2d(ctx0, res_hc, n_embd*hc, res_hc->ne[2]);
|
||||
res_hc = ggml_get_rows(ctx0, res_hc, inp_out_ids);
|
||||
res_hc = ggml_reshape_3d(ctx0, res_hc, n_embd, hc, res_hc->ne[1]);
|
||||
|
||||
Reference in new issue
Block a user