Daniël de Kok 48fec7b198 Unify attention output handling (#2343) ... - Always return the hidden states. - Create the output tensor inside the `attention` and `paged_attention` functions. This removes the difference between how the output is handled between attention (output parameter) and paged attention (return value). This also removes the assumption that the attention implementation can write to an output tensor (in preparation of FlashInfer).		2024-09-25 05:55:39 +00:00
..
adapters	feat: add ruff and resolve issue (#2262)	2024-09-25 05:46:24 +00:00
layers	Unify attention output handling (#2343)	2024-09-25 05:55:39 +00:00
models	Unify attention output handling (#2343)	2024-09-25 05:55:39 +00:00
pb	chore: add pre-commit (#1569)	2024-04-24 15:32:02 +03:00
utils	Handle GPTQ-Marlin loading in GPTQMarlinWeightLoader (#2300)	2024-09-25 05:55:39 +00:00
__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)	2024-09-25 05:46:24 +00:00
interceptor.py	Aligin the source code with main branch 2.0.4	2024-09-24 03:06:55 +00:00
server.py	Pr 2290 ci run (#2329)	2024-09-25 05:55:39 +00:00
tracing.py	Add OTLP Service Name Environment Variable (#2076)	2024-09-24 03:51:26 +00:00