CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

graph : fix assert in memory-less build_attn (#15590)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-08-26 17:45:17 +03:00
committed by GitHub
parent 62cef26ac5
commit 0373486dbc
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-graph.cpp
View File

@@ -1376,7 +1376,7 @@ ggml_tensor * llm_graph_context::build_attn(
// [TAG_NO_CACHE_PAD] // [TAG_NO_CACHE_PAD]
// TODO: if ubatch.equal_seqs() == true, we can split the three tensors below into ubatch.n_seqs_unq streams // TODO: if ubatch.equal_seqs() == true, we can split the three tensors below into ubatch.n_seqs_unq streams
assert(!ubatch.equal_seqs()); assert(!ubatch.equal_seqs() || (k_cur->ne[3] == 1 && k_cur->ne[3] == ubatch.n_seqs_unq));
ggml_tensor * q = q_cur; ggml_tensor * q = q_cur;
ggml_tensor * k = k_cur; ggml_tensor * k = k_cur;