yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-10-30 17:39:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Pipeline fixes for OMP_NUM_THREADS

Browse Source
This commit is contained in:
Jake Poznanski 2025-08-15 18:30:00 +00:00
parent b9238b8638
commit 7c98673972
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
olmocr/pipeline.py
View File

@ -611,6 +611,9 @@ async def vllm_server_task(model_name_or_path, args, semaphore, unknown_args=Non
*cmd, *cmd,
stdout=asyncio.subprocess.PIPE, stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE,
# OMP_NUM_THREADS needs to be 1, otherwise you could have contention if you are running multiple copies of olmOCR on a machine with several GPUS
env={**os.environ, "OMP_NUM_THREADS": "1"},
) )
# Ensure the subprocess is terminated on exit # Ensure the subprocess is terminated on exit
@ -643,7 +646,7 @@ async def vllm_server_task(model_name_or_path, args, semaphore, unknown_args=Non
if match := re.search(r"Running: (\d+)", line): if match := re.search(r"Running: (\d+)", line):
current_running = int(match.group(1)) current_running = int(match.group(1))
# Check for negative derivative (decrease in running requests), to not overload VLLM # Check for negative derivative (decrease in running requests), to not overload VLLM
if current_running < last_running_req: if current_running < last_running_req and not running_reqs_decreased:
running_reqs_decreased = True running_reqs_decreased = True
logger.info(f"Running requests decreased: {last_running_req} -> {current_running}") logger.info(f"Running requests decreased: {last_running_req} -> {current_running}")
last_running_req = current_running last_running_req = current_running