Skip to content

Try removing custom annotation #12386

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Try removing custom annotation #12386

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 1 addition & 15 deletions examples/qualcomm/oss_scripts/llama/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -659,21 +659,7 @@ def permute(w, heads):
tokenizer=tokenizer,
custom_annotations=custom_annotations,
)
# If hybrid and lookahead mode, we store kv output quant_attrs and apply to prefill output quant_attrs later
if i == 0 and args.model_mode in ["hybrid", "lookahead"]:
output_indices = 0
for node in llama_instance.llama_graph_module.graph.nodes:
if node.op == "output":
for output in node.args[0]:
kv_quant_attrs[output_indices] = output.args[1:]
output_indices += 1
break
custom_annotations = custom_annotations + (
partial(
annotate_prefill_kv_output,
kv_quant_attrs=kv_quant_attrs,
),
)

llama_instance.passes_job[TagQuantIO][QCOM_PASS_ACTIVATE_KEY] = True
llama_instance.passes_job[TagQuantIO][QCOM_PASS_ARGS_KWARGS_DEFAULTS_KEY][
"get_quant_io_dtype_fn"
Expand Down
Loading