ViperEkura
75304d084d
- add skip_no_fp8 (CUDA + fp8_mm kernel + cc 8.9+) to tests/conftest.py - use skip_no_cuda / skip_no_kernel / skip_no_fp8 directly in test modules - drop _GPU alias and tests.extension.conftest re-exports - remove unused imports (Union in hf_adapter, make_grpo_config in data conftest)
30 lines
652 B
Python
30 lines
652 B
Python
"""Shared fixtures for extension tests."""
|
|
|
|
import pytest
|
|
import torch
|
|
|
|
from astrai.config.model_config import AutoRegressiveLMConfig
|
|
from astrai.model.transformer import AutoRegressiveLM
|
|
|
|
D = 64
|
|
CFG = dict(
|
|
vocab_size=1000,
|
|
hidden_size=128,
|
|
num_attention_heads=2,
|
|
num_key_value_heads=1,
|
|
intermediate_size=256,
|
|
max_position_embeddings=64,
|
|
num_hidden_layers=2,
|
|
rms_norm_eps=1e-5,
|
|
attn_type="gqa",
|
|
ffn_type="mlp",
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def cuda_model():
|
|
config = AutoRegressiveLMConfig(**CFG)
|
|
model = AutoRegressiveLM(config).to(device="cuda", dtype=torch.bfloat16)
|
|
model.eval()
|
|
return model, config
|