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
This commit is contained in:
Wing Lian
2025-06-29 22:11:16 -04:00
committed by GitHub
parent 7563e1bd30
commit cb811f8bf1
6 changed files with 17 additions and 26 deletions

View File

@@ -20,12 +20,11 @@ jobs:
python_version: "3.11"
pytorch: 2.5.1
axolotl_extras:
- cuda: 124
cuda_version: 12.4.1
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.6.0
axolotl_extras: vllm
is_latest: true
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
@@ -88,8 +87,8 @@ jobs:
python_version: "3.11"
pytorch: 2.5.1
axolotl_extras:
- cuda: 124
cuda_version: 12.4.1
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.6.0
axolotl_extras:
@@ -146,8 +145,8 @@ jobs:
strategy:
matrix:
include:
- cuda: 124
cuda_version: 12.4.1
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.6.0
axolotl_extras:

View File

@@ -26,11 +26,11 @@ jobs:
fail-fast: false
matrix:
include:
- cuda: 124
cuda_version: 12.4.1
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.6.0
axolotl_extras: vllm
axolotl_extras:
num_gpus: 2
nightly_build: "true"
- cuda: 124

View File

@@ -195,12 +195,12 @@ jobs:
fail-fast: false
matrix:
include:
- cuda: 124
cuda_version: 12.4.1
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.6.0
num_gpus: 1
axolotl_extras: vllm
axolotl_extras:
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
@@ -247,8 +247,8 @@ jobs:
fail-fast: false
matrix:
include:
- cuda: 124
cuda_version: 12.4.1
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.6.0
num_gpus: 1
@@ -311,7 +311,7 @@ jobs:
python_version: "3.11"
pytorch: 2.6.0
num_gpus: 1
axolotl_extras: vllm
axolotl_extras:
steps:
- name: Checkout
uses: actions/checkout@v4