refactor: rebuild KV cache with three-layer separation architecture

- Replace CacheView/ContiguousCache/PageCache with SGLang-inspired design: KVStorage (flat token-level NHD buffers [n_layers, size, H, D]), ReqToTokenPool (index table [req_idx, pos] -> token_slot), Allocator + PrefixCache (slot allocation with LRU and prefix sharing)
- Add KVCache as pure dataclass passed to model: k_buffer, v_buffer, req_to_token, req_pool_indices, seq_lens, out_cache_loc
- PagePool orchestrates all three layers, supports contiguous mode (pre-allocated per-request blocks, default) and paged mode (page_size=1 or >1 with dynamic allocation and prefix caching)
- Attention layers now do raw buffer indexing instead of opaque write/gather method calls on CacheView objects
- Update executor.bind_tasks signature: seq_lens list + start_pos
- Rename paged_cache -> kv_cache throughout model/ and inference/

astrai/inference/engine.py

@@ -8,7 +8,7 @@ from typing import Any, AsyncGenerator, Dict, Generator, List, Optional, Tuple,
 import torch
 import torch.nn as nn
 
-from astrai.inference.core.cache import KVCache
+from astrai.inference.core.cache import PagePool
 from astrai.inference.core.scheduler import InferenceScheduler
 from astrai.inference.core.task import STOP
 from astrai.tokenize import AutoTokenizer
@@ -111,7 +111,7 @@ class InferenceEngine:
         tokenizer: AutoTokenizer,
         max_batch_size: int = 1,
         max_seq_len: Optional[int] = None,
-        cache: Optional[KVCache] = None,
+        cache: Optional[PagePool] = None,
     ):
         self.model = model
         self.tokenizer = tokenizer