fix bug
(cherry picked from commit 60d31cb0c268c4b733ab290e133e3763b65f090e)
This commit is contained in:
@@ -4873,10 +4873,13 @@ class DeepseekV4ForCausalLM(nn.Module):
|
||||
self.wo_a_fp8 = wo_a_fp8_gemm_enabled(quant_config)
|
||||
self.determine_num_fused_shared_experts()
|
||||
self.vision = None
|
||||
if config.model_type == "deepseek_v41" and config.vision_n_layers > 0:
|
||||
if (
|
||||
config.model_type == "deepseek_v41"
|
||||
and config.vision_n_layers > 0
|
||||
and not getattr(config, "language_model_only", False)
|
||||
):
|
||||
if (
|
||||
get_parallel().attn_cp_size != 1
|
||||
or get_parallel().pp_group.world_size != 1
|
||||
get_parallel().pp_group.world_size != 1
|
||||
or not get_moe_a2a_backend().is_none()
|
||||
):
|
||||
raise ValueError(
|
||||
|
||||
Reference in New Issue
Block a user