yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-10-11 16:22:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allowing more max tokens in pipeline for new models

Browse Source
This commit is contained in:
Jake Poznanski 2025-09-29 22:12:27 +00:00
parent 7f4b728dcd
commit b5b1de98dd
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
olmocr/pipeline.py
View File

@ -105,7 +105,7 @@ class PageResult:
async def build_page_query(local_pdf_path: str, page: int, target_longest_image_dim: int, image_rotation: int = 0) -> dict:
MAX_TOKENS = 4500
MAX_TOKENS = 8000
assert image_rotation in [0, 90, 180, 270], "Invalid image rotation provided in build_page_query"
# Allow the page rendering to process in the background, but limit the number of workers otherwise you can overload the system
@ -678,7 +678,7 @@ async def vllm_server_task(model_name_or_path, args, semaphore, unknown_args=Non
# Check if we should release the semaphore
should_release = (
server_printed_ready_message
and last_queue_req <= int(peak_running_req * 0.1)
and last_queue_req <= int(peak_running_req * 0.2)
and time.time() - last_semaphore_release > 30
and semaphore.locked()
and (last_running_req == 0 or running_reqs_decreased)