Skip to content

[CI/Build][CPU] Fix CPU CI by lazy importing triton FP8 kernels #11618

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 30, 2024
Merged

[CI/Build][CPU] Fix CPU CI by lazy importing triton FP8 kernels #11618

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ccc4227
fix cpu ci
bigPYJ1151 Dec 30, 2024
b368b24
fix format
bigPYJ1151 Dec 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions vllm/model_executor/layers/quantization/fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,6 @@
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig, QuantizeMethodBase)
from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
from vllm.model_executor.layers.quantization.utils.fp8_utils import (
apply_w8a8_block_fp8_linear)
from vllm.model_executor.layers.quantization.utils.marlin_utils_fp8 import (
apply_fp8_marlin_linear, prepare_fp8_layer_for_marlin)
from vllm.model_executor.layers.quantization.utils.quant_utils import (
Expand Down Expand Up @@ -337,6 +335,9 @@ def apply(self,
size_k=layer.input_size_per_partition,
bias=bias)

# Note: lazy import to avoid triton import error.
from vllm.model_executor.layers.quantization.utils.fp8_utils import (
apply_w8a8_block_fp8_linear)
if self.block_quant:
assert self.quant_config.weight_block_size is not None
return apply_w8a8_block_fp8_linear(
Expand Down
Loading