Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

qwen35: use post-norm hidden state for MTP (#24025)

Browse Source 
* qwen35: use post-norm hidden state for MTP

* rename pre_norm to nextn

* fix step35
This commit is contained in:
Aman Gupta
2026-06-04 01:29:09 +08:00
committed by GitHub
parent c8d6a00636
commit 166fe29492
12 changed files with 132 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.h
+7 -7
View File
@@ -84,8 +84,8 @@ struct llama_context {
float * get_embeddings_ith(int32_t i);
float * get_embeddings_seq(llama_seq_id seq_id);
float * get_embeddings_pre_norm();
float * get_embeddings_pre_norm_ith(int32_t i);
float * get_embeddings_nextn();
float * get_embeddings_nextn_ith(int32_t i);
llama_token * get_sampled_tokens() const;
llama_token get_sampled_token_ith(int32_t idx);
@@ -110,7 +110,7 @@ struct llama_context {
void set_abort_callback(bool (*abort_callback)(void * data), void * abort_callback_data);
void set_embeddings (bool value);
void set_embeddings_pre_norm(bool value, bool masked);
void set_embeddings_nextn(bool value, bool masked);
void set_causal_attn(bool value);
void set_warmup(bool value);
@@ -282,10 +282,10 @@ private:
// populated only when pooling_type == LLAMA_POOLING_TYPE_NONE
buffer_view<float> embd = {nullptr, 0};
// hidden state before the final output norm (2-dimensional array: [n_outputs][n_embd])
// populated only when cparams.embeddings_pre_norm is enabled and the model graph
// sets llm_graph_result::t_h_pre_norm
buffer_view<float> embd_pre_norm = {nullptr, 0};
// hidden state required by the nextn layers (2-dimensional array: [n_outputs][n_embd])
// populated only when cparams.embeddings_nextn is enabled and the model graph
// sets llm_graph_result::t_h_nextn
buffer_view<float> embd_nextn = {nullptr, 0};
struct sampling_info {
// !samplers.empty() to check if any samplers are active