mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-10-10 23:45:23 +00:00
- Avoid theoretical hang in batcher loop - Avoid a couple of clones in py server generate method - Keep attention mask tensors as integers |
||
---|---|---|
.. | ||
models | ||
pb | ||
__init__.py | ||
cache.py | ||
cli.py | ||
server.py | ||
utils.py |