[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()
|
||||
|
||||
@@ -322,6 +322,7 @@ class MambaHybridModelState(DefaultModelState):
|
||||
kv_cache_config=kv_cache_config,
|
||||
seq_lens_cpu_upper_bound=seq_lens_cpu_upper_bound,
|
||||
dcp_local_seq_lens=input_batch.dcp_local_seq_lens,
|
||||
positions=input_batch.positions,
|
||||
model_specific_attn_metadata=mamba_attn_metadata,
|
||||
for_cudagraph_capture=for_capture,
|
||||
rswa_prefix_lens=input_batch.prompt_lens,
|
||||
|
||||
Reference in New Issue
Block a user