fix: pass v_head_dim to MHA KV pools and validate MiMo HiCache geometry (#23173)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.6
parent
bf5e71dcec
commit
4befc31408
@@ -536,6 +536,7 @@ class ModelRunnerKVCacheMixin:
|
||||
get_attention_tp_size()
|
||||
),
|
||||
head_dim=self.model_config.head_dim,
|
||||
v_head_dim=self.model_config.v_head_dim,
|
||||
layer_num=self.num_effective_layers,
|
||||
device=self.device,
|
||||
enable_memory_saver=self.server_args.enable_memory_saver,
|
||||
@@ -555,6 +556,7 @@ class ModelRunnerKVCacheMixin:
|
||||
get_attention_tp_size()
|
||||
),
|
||||
head_dim=self.model_config.head_dim,
|
||||
v_head_dim=self.model_config.v_head_dim,
|
||||
layer_num=self.num_effective_layers,
|
||||
device=self.device,
|
||||
enable_memory_saver=self.server_args.enable_memory_saver,
|
||||
|
||||
Reference in New Issue
Block a user