text-generation-inference/server/text_generation_server
drbh 0acac5cb7a
feat: improve temperature logic in chat (#1749)
This PR adds support for `do_sample` to chat to enable greedy sampling

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-04-25 15:31:35 +02:00
..
models Idefics2. (#1756) 2024-04-23 23:04:44 +02:00
pb chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
utils feat: improve temperature logic in chat (#1749) 2024-04-25 15:31:35 +02:00
__init__.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
cache.py fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
cli.py Fp8 Support (#1726) 2024-04-12 08:13:30 +02:00
interceptor.py v2.0.0 (#1736) 2024-04-12 18:38:34 +02:00
server.py Adding Llava-Next (Llava 1.6) with full support. (#1709) 2024-04-09 21:32:00 +02:00
tracing.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00