EngineX-Cambricon/enginex-mlu370-vllm
10
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity

add deepseekv3 and llama4

Browse Source
This commit is contained in:
Chranos
2026-02-11 14:37:00 +08:00
parent 00083a1c76
commit 5c980830a0
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm-v0.6.2/vllm_mlu/vllm_mlu/model_executor/models/llama4.py
View File

@@ -9,7 +9,8 @@ from vllm.model_executor.layers.layernorm import RMSNorm
from vllm_mlu.model_executor.layers.feed_forward import FeedForward from vllm_mlu.model_executor.layers.feed_forward import FeedForward
from vllm_mlu.mlu_hijack_utils import MluHijackObject from vllm_mlu.mlu_hijack_utils import MluHijackObject
from vllm.distributed import tensor_model_parallel_all_reduce from vllm.distributed import tensor_model_parallel_all_reduce
from vllm.model_executor.model_loader.weight_utils import default_weight_loader from vllm.model_executor.model_loader.weight_utils import (
default_weight_loader, maybe_remap_kv_scale_name)
from vllm.model_executor.models.llama4 import ( from vllm.model_executor.models.llama4 import (
Llama4Attention, Llama4DecoderLayer, Llama4ForCausalLM, Llama4Attention, Llama4DecoderLayer, Llama4ForCausalLM,
Llama4Model, Llama4MoE) Llama4Model, Llama4MoE)