tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-29 05:33:37 -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.cpp
View File

@@ -694,7 +694,7 @@ bool llama_context::apply_adapter_cvec(
return cvec.apply(model, data, len, n_embd, il_start, il_end);
}
llm_graph_result_i * llama_context::process_ubatch(const llama_ubatch & ubatch, llm_graph_type gtype, llama_memory_context_i * mctx, ggml_status & ret) {
llm_graph_result * llama_context::process_ubatch(const llama_ubatch & ubatch, llm_graph_type gtype, llama_memory_context_i * mctx, ggml_status & ret) {
if (mctx && !mctx->apply()) {
LLAMA_LOG_ERROR("%s: failed to apply memory context\n", __func__);
ret = GGML_STATUS_FAILED;
@@ -1363,7 +1363,7 @@ ggml_cgraph * llama_context::graph_reserve(uint32_t n_tokens, uint32_t n_seqs, u
}
llm_graph_params llama_context::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 {