tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-28 21:23:55 -04:00
Code Issues Packages Projects Releases Wiki Activity

graph : refactor context to not pass gf explicitly (#14629)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-18 08:29:28 +03:00
committed by GitHub
parent 09651d09ff
commit 8f974bc1e9
5 changed files with 295 additions and 341 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-context.h
View File

@@ -94,7 +94,7 @@ struct llama_context {
// if memory_context is provided, it will be applied first to the context's memory
// ret contains the status of the graph computation
// returns nullptr only if ret != GGML_STATUS_SUCCESS
llm_graph_result_i * process_ubatch(
llm_graph_result * process_ubatch(
const llama_ubatch & ubatch,
llm_graph_type gtype,
llama_memory_context_i * mctx,
@@ -199,7 +199,7 @@ public:
private:
llm_graph_params graph_params(
llm_graph_result_i * res,
llm_graph_result * res,
const llama_ubatch & ubatch,
const llama_memory_context_i * mctx,
llm_graph_type gtype) const;