[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:
Jiangyun Zhu
2026-10-01 02:59:37 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 Thomas Parnell
parent 08d77cad7b
commit cb6458c5ce
45 changed files with 201 additions and 1476 deletions
@@ -418,12 +418,6 @@ class InternS2MobiusForCausalLM(Qwen3_5ForCausalLMBase):
self.quant_config = vllm_config.quant_config
self.scheduler_config = vllm_config.scheduler_config
if vllm_config.cache_config.mamba_cache_mode == "all":
raise NotImplementedError(
"Intern-S2-Mobius does not support 'all' prefix caching; "
"use '--mamba-cache-mode=align' instead."
)
nn.Module.__init__(self)
self.config = config
self.model = InternS2MobiusModel(