tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

upgrade trl==0.19.1 (#2892) [skip ci]

Browse Source 
* upgrade trl==0.19.1

* add vllm for tests for grpo

* fixes to work with latest trl

* need data_parallel_size config too

* support for vllm_mode for server / colocate

* vllm settings for colocate

* relax vllm version

* bump min hf hub for latest vllm support

* add hints on string literal for vllm mode

* use latest transformers 4.53.2

* tweak acceptable loss on flaky test_ds_zero3_packed test

* don't run flaky vllm/grpo tests for now
This commit is contained in:
Wing Lian
2025-07-14 09:23:42 -04:00
committed by GitHub
parent 41664c7c4c
commit 5081db7f8a
9 changed files with 43 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
.github/workflows/multi-gpu-e2e.yml vendored
View File

@@ -33,6 +33,13 @@ jobs:
axolotl_extras:
num_gpus: 2
nightly_build: "true"
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"
pytorch: 2.7.0
axolotl_extras: vllm
num_gpus: 2
nightly_build: "true"
- cuda: 126
cuda_version: 12.6.3
python_version: "3.11"