chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

Rename triton_fused_moe -> fused_moe_triton (#2163)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-11-24 08:12:35 -08:00
committed by GitHub
parent fe5d3e818f
commit be0124bda0
76 changed files with 19 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/models/mixtral.py
+1 -1
View File
@@ -25,6 +25,7 @@ from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from sglang.srt.layers.fused_moe_triton import FusedMoE
from sglang.srt.layers.layernorm import RMSNorm
from sglang.srt.layers.linear import (
QKVParallelLinear,
@@ -35,7 +36,6 @@ 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.torchao_utils import apply_torchao_config_
from sglang.srt.layers.triton_fused_moe import FusedMoE
from sglang.srt.layers.vocab_parallel_embedding import (
ParallelLMHead,
VocabParallelEmbedding,