TransformerEngine-FL/.github/configs/cuda.yml at b8da5252fe9a19b197f0c95ed89ffa505f260966 · BrianPei/TransformerEngine-FL · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
# CUDA Hardware Configuration for TransformerEngine-FL
# Refactored for BAAI DGX A100 Nodes
# This file defines environment variables, volumes, and test filters for TE tests.

hardware_name: cuda
display_name: "NVIDIA CUDA (A100)"

ci_image: harbor.baai.ac.cn/flagscale/cuda12.8.1-torch2.7.1-python3.10-te2.9:20260209

# Runner labels for self-hosted A100 node
runner_labels:
  - self-hosted
  - Linux
  - X64
  - nvidia
  - gpu-8

# Container volumes
container_volumes:
  - .:/opt/transformerengine
  - ./ci_logs:/logs
  - /home/flagscale_cicd/data:/opt/data

# Container options
container_options: >-
  --privileged
  --gpus all
  --shm-size=500g
  --ipc=host
  --ulimit memlock=-1
  --ulimit stack=67108864
  --user root

# Device types
device_types:
  - a100

# Environment variables
env_vars:
  NVTE_FRAMEWORK: pytorch
  TE_WITH_NCCL: 1
  NVTE_PROJECT_BUILDING: 1
  TE_FL_SKIP_CUDA: 0

# Test matrix configuration
test_matrix:
  l0_pytorch:
    path: "qa/L0_pytorch_unittest/test.sh"
    ignored_tests:
      - test_sanity_layernorm_mlp
      - test_sanity_gpt
      - test_sanity_bert
      - test_sanity_T5
      - test_sanity_amp_and_nvfuser
      - test_sanity_drop_path
      - test_layernorm_mlp_accuracy
      - test_grouped_linear_accuracy
      - test_gpt_accuracy
      - test_basic_linear
      - test_layer_norm