tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-19 22:36:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

batch : rework llama_batch_allocr (#14153)

Browse Source 
* batch : rework llama_batch_allocr

ggml-ci

* cont : move validation inside class

ggml-ci

* cont : move output counting to class

ggml-ci

* cont : minor

ggml-ci

* batch : add TODOs

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-13 13:47:55 +03:00
committed by GitHub
parent b7cc7745e3
commit 60c666347b
7 changed files with 162 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llama-graph.h
View File

@@ -378,7 +378,7 @@ struct llm_graph_params {
const llama_memory_state_i * mstate;
const llama_cross * cross;
int32_t n_outputs;
uint32_t n_outputs;
const llm_graph_cb & cb;
};
@@ -412,8 +412,8 @@ struct llm_graph_context {
const float norm_eps;
const float norm_rms_eps;
const int32_t n_tokens;
const int32_t n_outputs;
const int64_t n_tokens;
const int64_t n_outputs;
const int32_t n_ctx_orig; // yarn
const enum llama_pooling_type pooling_type;