[Model] add GLM-5.3-Flash support (#53906)

This commit is contained in:
Jiangyun Zhu
2026-09-03 09:40:35 -07:00
committed by GitHub
parent da8ec28268
commit 98ed0856f3
94 changed files with 17927 additions and 266 deletions
+1
View File
@@ -1160,6 +1160,7 @@ class GPUModelRunner(
kernel_block_sizes=self._kernel_block_sizes,
runner_only_attn_layers=self.runner_only_attn_layers,
static_forward_context=self.compilation_config.static_forward_context,
num_blocks=self.kv_cache_config.num_blocks,
)
def _zero_block_ids(self, block_ids: list[int]) -> None: