Optimize broadcast & Reorg code (#1598)

This commit is contained in:
Lianmin Zheng
2024-10-07 13:05:53 -07:00
parent 3ff641132e
commit ebbc42d989
3 changed files with 55 additions and 47 deletions

View File

@@ -148,6 +148,6 @@ def get_act_fn(
if not is_flashinfer_available():
logger.info(
"FlashInfer is not available on Non-NV GPUs. Fallback to other kernel libraries."
"FlashInfer is not available on Non-NV platforms. Fallback to other kernel libraries."
)
from vllm.model_executor.layers.activation import GeluAndMul, SiluAndMul