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:
Georgi Gerganov authored and GitHub committed 2026-10-06 14:08:54 +03:00
1 parent d7a695ef67
commit f0c41e0168
20 files changed
+59 -62

No files matched your search

+2 -3
View File
@@ -650,8 +650,7 @@ llama_model_glm5_next::graph::graph(const llama_model & model, const llm_graph_p
// narrow to the output tokens, then collapse the streams
// Unmasked nextn embeddings need all rows.
const bool narrow_early = inp_out_ids && (!cparams.embeddings_nextn || cparams.embeddings_nextn_masked);
if (narrow_early) {
if (crop_before_nextn(inp_out_ids)) {
ggml_tensor * flat = ggml_reshape_2d(ctx0, inpL, n_embd*hc, n_tokens);
flat = ggml_get_rows(ctx0, flat, inp_out_ids);
inpL = ggml_reshape_3d(ctx0, flat, n_embd, hc, n_outputs);
@@ -666,7 +665,7 @@ llama_model_glm5_next::graph::graph(const llama_model & model, const llm_graph_p
cb(cur, "h_nextn", -1);
res->t_h_nextn = cur;
if (inp_out_ids && !narrow_early) {
if (crop_after_nextn(inp_out_ids)) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
}
cb(cur, "result_norm", -1);