feat: update other MoE models deps (#2156)

2024-11-24 21:36:34 +08:00
parent c211e7b669
commit e3938b2f9c
10 changed files with 28 additions and 14 deletions
@@ -26,7 +26,6 @@ from vllm.distributed import (
    get_tensor_model_parallel_world_size,
    tensor_model_parallel_all_reduce,
 )
-from vllm.model_executor.layers.fused_moe import fused_moe
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader

@@ -41,6 +40,7 @@ from sglang.srt.layers.linear import (
 from sglang.srt.layers.logits_processor import LogitsProcessor
 from sglang.srt.layers.quantization.base_config import QuantizationConfig
 from sglang.srt.layers.radix_attention import RadixAttention
+from sglang.srt.layers.triton_fused_moe import fused_moe
 from sglang.srt.layers.vocab_parallel_embedding import (
    ParallelLMHead,
    VocabParallelEmbedding,