Skip to content

Conversation

@CSY-ModelCloud
Copy link
Collaborator

No description provided.

@Qubitium Qubitium changed the title add tests runner Add CI Runner Jun 19, 2024
@Qubitium Qubitium merged commit faabfc8 into main Jun 20, 2024
@Qubitium Qubitium deleted the csy-runner branch June 20, 2024 14:55
DeJoker pushed a commit to DeJoker/GPTQModel that referenced this pull request Jul 19, 2024
* update table's style

* fix spell

* add run tests action

* use sudo

* update work flows

* remove apt

* update container

* actions/checkout@v4

* fix path

* remove cd

* nvidia-smi

* remove nvidia-smi

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* Create run_tests_2

* Rename run_tests_2 to run_tests_2.yml

* Update run_tests_2.yml

* Update run_tests_2.yml

* Update run_tests_2.yml

* test a small model

* Update run_tests_2.yml

* Update run_tests_2.yml

* Update run_tests_2.yml

* remove cache

* Update run_tests_2.yml

* Update run_tests_2.yml

* move to requirements.txt

* Delete .github/workflows/run_tests_2.yml

* Update run_tests.yml

* Update run_tests.yml

* Update requirements.txt

* Update run_tests.yml

* use modelcloud/gptqmodel:github-ci-v1

* use pytest

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* use pytorch/pytorch:2.3.1-cuda12.1-cudnn8-devel

* Update run_tests.yml

* Update run_tests.yml

* add run-test need: build

* Update run_tests.yml

* install dep before test

* use corca-ai/local-cache@v2

* Update run_tests.yml

* Update run_tests.yml

* Update run_tests.yml

* test cache build

* test build is exist

* disable compile for test

* list after cache

* base: /tmp/gptqmodel

* Update run_tests.yml

* Update run_tests.yml

* run test one by one

* Update run_tests.yml

* parameterized

* model has been fixed

* use gpu 0

* remove gptqmodel_cuda_available

* show which file is running

* fix quant desc_act

* in steps

* update format

* fix dir

---------

Co-authored-by: Qubitium-ModelCloud <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants