[Core] Remove deprecated mamba_cache_mode "all" (#58997)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
Thomas Parnell
parent
08d77cad7b
commit
cb6458c5ce
@@ -1079,12 +1079,7 @@ class MambaSpec(KVCacheSpec):
|
||||
return None
|
||||
|
||||
def max_memory_usage_bytes(self, vllm_config: VllmConfig) -> int:
|
||||
if vllm_config.cache_config.mamba_cache_mode == "all":
|
||||
max_model_len = vllm_config.model_config.max_model_len
|
||||
return (
|
||||
cdiv(max_model_len, self.block_size) + self.num_speculative_blocks
|
||||
) * self.page_size_bytes
|
||||
elif vllm_config.cache_config.mamba_cache_mode == "align":
|
||||
if vllm_config.cache_config.mamba_cache_mode == "align":
|
||||
return self.page_size_bytes * (
|
||||
2 + self.num_speculative_blocks + self.num_prefill_checkpoint_blocks
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user