Skip to content

Make prefill step size configurable via EXO_PREFILL_STEP_SIZE (#2141) #2155

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

Make prefill step size configurable via EXO_PREFILL_STEP_SIZE (#2141) #2155

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
3 changes: 2 additions & 1 deletion src/exo/worker/engines/mlx/generator/generate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import contextlib
import functools
import math
import os
import time
import uuid
from typing import Callable, Generator, cast, get_args
Expand Down Expand Up @@ -331,7 +332,7 @@ def combined_progress_callback(processed: int, total: int) -> None:

is_pipeline = _has_pipeline_communication_layer(model)

prefill_step_size = 4096
prefill_step_size = int(os.getenv("EXO_PREFILL_STEP_SIZE", "4096"))

try:
if is_pipeline and num_tokens >= prefill_step_size:
Expand Down