[Feature] Support MiniMax-H3 Turbo LoRA with DLO (#6550)
Signed-off-by: mglyn <1203789601@qq.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
1 parent
7439ed41c2
commit
59cf3add40
7 files changed
+124
-9
No files matched your search
@@ -724,8 +724,6 @@ class MiniMaxH3Pipeline(
|
||||
offload_modes.append("model-level CPU offload (--enable-cpu-offload)")
|
||||
if getattr(od_config, "enable_layerwise_offload", False):
|
||||
offload_modes.append("layerwise offload (--enable-layerwise-offload)")
|
||||
if getattr(od_config, "enable_distributed_layerwise_offload", False):
|
||||
offload_modes.append("distributed layerwise offload (--enable-distributed-layerwise-offload)")
|
||||
loaded = load_minimax_h3_turbo_lora(
|
||||
partition=self.partition,
|
||||
lora_request=lora_request,
|
||||
|
||||
Reference in new issue
Block a user