text-generation-inference/server/text_generation_server
Nicolas Patry b70ae0969f
Prefix caching (#2402)
* Prefix caching WIP

* Fixing prefix attention.

* Fixing flashinfer import.

* Fixing black.

* Fixing medusa (still wrong outputs, but functional).

* Just medusa values now.

* Fixing medusa without prefix caching.

* Fixing prefix caching.

* Medusa requires reshaping.

* Removing the logs.

* Remove router.nix

* Fixup:

- Remove logs
- Disable VLMs (they do not work)
- Disable prefix caching when user wants prefill logprobs.

* Update flake.lock

---------

Co-authored-by: Daniël de Kok <me@danieldk.eu>
2024-08-20 11:15:30 +02:00
..
adapters feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
layers Prefix caching (#2402) 2024-08-20 11:15:30 +02:00
models Prefix caching (#2402) 2024-08-20 11:15:30 +02:00
pb chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
utils fix: allocate tmp based on sgmv kernel if available (#2345) 2024-08-12 17:24:32 +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 feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
interceptor.py v2.0.0 (#1736) 2024-04-12 18:38:34 +02:00
server.py Upgrading exl2. (#2415) 2024-08-14 11:58:08 +02:00
tracing.py Add OTLP Service Name Environment Variable (#2076) 2024-06-25 09:33:01 +02:00