CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : separate compute buffer reserve from fattn check (#15696)

Browse Source 
Exposes ggml_backend_sched_split_graph() to allow splitting the graph without allocating compute buffers and uses it to split the graph for the automatic Flash Attention check.
This commit is contained in:
Diego Devesa
2025-08-31 06:49:03 -07:00
committed by GitHub
parent 7d3c9f2b21
commit 9777032dcc
4 changed files with 64 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-context.h
View File

@@ -196,7 +196,7 @@ public:
ggml_status graph_compute(ggml_cgraph * gf, bool batched);
// reserve a graph with a dummy ubatch of the specified size
ggml_cgraph * graph_reserve(uint32_t n_tokens, uint32_t n_seqs, uint32_t n_outputs, const llama_memory_context_i * mctx);
ggml_cgraph * graph_reserve(uint32_t n_tokens, uint32_t n_seqs, uint32_t n_outputs, const llama_memory_context_i * mctx, bool split_only = false);
private:
llm_graph_params graph_params(