tabbyAPI-ollama/common
kingbri c474076b22 Concurrency: Remove release_semaphore method
At any point for any request cancellation, the semaphore will be
decremented. This is an issue since an arbitrary request can desync
the semaphore, causing multiple tasks to be processed at once and
break generation.

Remove this from the networking handlers and therefore, remove the
release_semaphore function itself.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-05-19 10:42:26 -04:00
..
args.py Tree: Format 2024-03-13 00:02:55 -04:00
auth.py API: Cleanup permission endpoint 2024-03-18 15:13:26 -04:00
concurrency.py Concurrency: Remove release_semaphore method 2024-05-19 10:42:26 -04:00
config.py Tree: Update to cleanup globals 2024-03-12 23:59:30 -04:00
downloader.py Downloader: Cleanup on exception 2024-04-30 23:26:22 -04:00
gen_logging.py Tree: Format 2024-03-13 23:33:18 -04:00
logger.py API: Add HuggingFace downloader 2024-04-29 01:15:02 -04:00
model.py Common: Migrate request utils to networking 2024-03-21 23:21:57 -04:00
networking.py Concurrency: Remove release_semaphore method 2024-05-19 10:42:26 -04:00
sampling.py Sampling: Copy over iterable overrides 2024-05-17 21:38:28 -04:00
signals.py Signal: Fix signal handlers for uvicorn 2024-03-16 23:23:31 -04:00
templating.py Templates: Migrate to class 2024-04-21 23:28:14 -04:00
transformers_utils.py Tree: Add transformers_utils 2024-04-20 00:07:39 -04:00
utils.py Sampling: Copy over iterable overrides 2024-05-17 21:38:28 -04:00