text-generation-inference/server/text_generation_server
Nicolas Patry 732da6942b Remove lots of dead code, move triton to hard requirement
- Added option to upload to hub directly after quantizing.
2023-06-14 14:55:45 +02:00
..
models No one saw that, therefore it didn't happen. 2023-06-14 12:23:30 +02:00
pb feat(server): clear cache on error (#143) 2023-03-28 11:29:35 +02:00
utils Remove lots of dead code, move triton to hard requirement 2023-06-14 14:55:45 +02:00
__init__.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
cache.py feat(server): clear cache on error (#143) 2023-03-28 11:29:35 +02:00
cli.py Remove lots of dead code, move triton to hard requirement 2023-06-14 14:55:45 +02:00
interceptor.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
server.py feat(server): support vectorized warpers in flash causal lm (#317) 2023-05-26 12:30:27 +02:00
tracing.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00