[Core][Mamba] Remove leftovers of mamba_cache_mode="all" (#60043)

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <zhujiangyun@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Jiangyun Zhu
2026-10-13 00:58:59 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent bc3ddb198a
commit 2cc2e68d1c
33 changed files with 161 additions and 344 deletions
+2 -6
View File
@@ -45,7 +45,7 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
)
from vllm.sequence import IntermediateTensors
from .interfaces import HasInnerState, IsHybrid, SupportsMambaPrefixCaching
from .interfaces import HasInnerState, IsHybrid
from .utils import AutoWeightsLoader, WeightsMapper, maybe_prefix
@@ -833,7 +833,7 @@ class Zamba2Model(nn.Module):
return hidden_states
class Zamba2ForCausalLM(nn.Module, HasInnerState, IsHybrid, SupportsMambaPrefixCaching):
class Zamba2ForCausalLM(nn.Module, HasInnerState, IsHybrid):
"""Zamba2 model with causal language modeling head.
This class wraps the core Zamba2 model and adds:
@@ -911,10 +911,6 @@ class Zamba2ForCausalLM(nn.Module, HasInnerState, IsHybrid, SupportsMambaPrefixC
LoRA and scheduler settings
prefix: Optional prefix for parameter names
Raises:
AssertionError: If prefix caching is enabled
(not supported by Mamba)
"""
config = vllm_config.model_config.hf_config