vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : better express the KV cache dependencies in the graph

Browse source
This commit is contained in:
Georgi Gerganov 2023-09-04 21:44:48 +03:00
parent 60c2ef6d92
commit f3a84b2e0d
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 41 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml.c
View file

@ -5213,6 +5213,8 @@ struct ggml_tensor * ggml_view_tensor(
result->nb[i] = src->nb[i];
}
result->op = GGML_OP_VIEW;
return result;
}