Wing Lian cb811f8bf1 upgrade to flash-attn 2.8.0.post2 (#2828) ...

* upgrade to flash-attn 2.8.0.post2

* use cu126 with torch 2.6

* seems vllm 0.8.5.post1 not compatible with cuda12.6.3 and torch 2.6

* cu126 + torch 2.6 as the default

* use cu126 for multigpu w torch 2.6 too

* drop vllm for now from ci for now

2025-06-29 22:11:16 -04:00

..

ISSUE_TEMPLATE

github urls (#1734)

2024-07-11 09:19:29 -04:00

workflows

upgrade to flash-attn 2.8.0.post2 (#2828)

2025-06-29 22:11:16 -04:00

CODE_OF_CONDUCT.md

add templates, CoC and contributing guide (#126)

2023-08-15 07:41:05 -04:00

CONTRIBUTING.md

refactor README; hardcode links to quarto docs; add additional quarto doc pages (#2295)

2025-01-30 12:49:21 -05:00

FUNDING.yml

Update FUNDING.yml [skip ci]

2024-01-26 20:00:28 -05:00

PULL_REQUEST_TEMPLATE.md

update PR template so we can capture twitter or discord handles (#1121) [skip ci]

2024-01-14 16:19:01 -05:00

release-drafter.yml

add release draft template for gh

2023-05-30 15:10:19 -04:00

SECURITY.md

add templates, CoC and contributing guide (#126)

2023-08-15 07:41:05 -04:00

SUPPORT.md

add templates, CoC and contributing guide (#126)

2023-08-15 07:41:05 -04:00