CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : minor simplify

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-18 14:53:02 +02:00
parent befe14f06f
commit 9e50456e19
4 changed files with 22 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/llama-model.cpp
View File

@@ -3841,19 +3841,18 @@ struct llm_build_context {
const enum llama_pooling_type pooling_type;
const enum llama_rope_type rope_type;
ggml_context_ptr & ctx;
ggml_context * ctx0 = nullptr;
ggml_context * ctx0 = nullptr;
llama_graph_result res;
// TODO: consider making the entire interface noexcept
llm_build_context(
ggml_context_ptr & ctx,
llama_graph_i & lgf,
const llama_model & model,
const llama_cparams & cparams,
const llama_ubatch & ubatch,
bool worst_case) :
ggml_context * ctx,
llama_graph_i & lgf,
const llama_model & model,
const llama_cparams & cparams,
const llama_ubatch & ubatch,
bool worst_case) :
lgf (lgf),
model (model),
hparams (model.hparams),
@@ -3885,8 +3884,7 @@ struct llm_build_context {
flash_attn (cparams.flash_attn),
pooling_type (cparams.pooling_type),
rope_type (hparams.rope_type),
ctx (ctx),
ctx0 (this->ctx.get()) {
ctx0 (ctx) {
}
// TODO: tmp
@@ -10937,7 +10935,7 @@ struct llm_build_context {
};
llama_graph_result llama_model::build_graph(
ggml_context_ptr & ctx,
ggml_context * ctx,
llama_graph_i & lgf,
const llama_cparams & cparams,
const llama_ubatch & ubatch,