[Model] add GLM-5.3-Flash support (#53906)
This commit is contained in:
@@ -696,6 +696,7 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
attn_groups_iter=(g for groups in self.attn_groups for g in groups),
|
||||
kernel_block_sizes=self.kernel_block_sizes,
|
||||
static_forward_context=self.compilation_config.static_forward_context,
|
||||
num_blocks=self.kv_cache_config.num_blocks,
|
||||
)
|
||||
|
||||
@torch.inference_mode()
|
||||
|
||||
Reference in New Issue
Block a user