refactor: split infer core into subpackages by concern

- Eliminate core/ directory into cache/, runtime/, network/ subpackages plus flat modules
- Split cache.py (647 lines) into cache/{buffer,strategy,pool}.py by layer
- Add explicit ContiguousStrategy, make AllocationStrategy a real ABC
- Move TaskCacheState to cache/strategy.py, drop string forward references
- Rename api/ to network/, server.py to app.py
- Move sample.py into runtime/ alongside executor and graph
- Simplify TaskCacheManager.__init__ to single pool param
- Expose pool.strategy and pool.req_pool as public properties
- Fix KVCache import in attention_backend.py (TYPE_CHECKING guard)
- Fix steady-state decode reading uninitialized position_ids on first step

astrai/model/components/attention.py

@@ -8,7 +8,7 @@ from torch import Tensor
 from astrai.extension import attention
 from astrai.extension.rotary_backend import apply_rotary_emb
 from astrai.factory import BaseFactory
-from astrai.inference.core.cache import KVCache
+from astrai.inference.cache import KVCache
 from astrai.model.components.linear import Linear
 from astrai.model.components.norm import RMSNorm
 

astrai/model/components/decoder_block.py

@@ -4,7 +4,7 @@ from typing import Optional, TypedDict
 import torch.nn as nn
 from torch import Tensor
 
-from astrai.inference.core.cache import KVCache
+from astrai.inference.cache import KVCache
 from astrai.model.components.attention import AttnFactory
 from astrai.model.components.mlp import FFNFactory, RouterStats
 from astrai.model.components.norm import RMSNorm

astrai/model/transformer.py

@@ -5,7 +5,7 @@ import torch.nn as nn
 from torch import Tensor
 
 from astrai.config.model_config import AutoRegressiveLMConfig
-from astrai.inference.core.cache import KVCache
+from astrai.inference.cache import KVCache
 from astrai.model.automodel import AutoModel, ModelFactory
 from astrai.model.components.decoder_block import DecoderBlock
 from astrai.model.components.embedding import Embedding