Skip to content

Commit dd8bb77

Browse files
Di Xu (SWE)facebook-github-bot
authored andcommitted
Add support to export XNNPACK based static_llama (#7535)
Summary: Add support to export XNNPACK based static_llama - static_llama is the QNN backend hybrid/prefill+decode model with KV cache as the inference input - https://www.internalfb.com/code/fbsource/fbcode/executorch/examples/qualcomm/oss_scripts/llama2/model/static_llama.py Reviewed By: tarun292 Differential Revision: D67867190
1 parent 68c0208 commit dd8bb77

File tree

1 file changed

+8
-1
lines changed

1 file changed

+8
-1
lines changed

examples/models/llama/export_llama_lib.py

Lines changed: 8 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,14 @@
7979
verbosity_setting = None
8080

8181

82-
EXECUTORCH_DEFINED_MODELS = ["stories110m", "llama2", "llama3", "llama3_1", "llama3_2"]
82+
EXECUTORCH_DEFINED_MODELS = [
83+
"stories110m",
84+
"llama2",
85+
"llama3",
86+
"llama3_1",
87+
"llama3_2",
88+
"static_llama",
89+
]
8390
TORCHTUNE_DEFINED_MODELS = ["llama3_2_vision"]
8491

8592

0 commit comments

Comments
 (0)