perf: use int32 paged KV indices

- store page-table, request-row, and cache-location indices as int32
- preserve CUDA graph replay with bit-exact logits and KV cache coverage
- improve B=1 decode latency by 1-6% across 1K-32K contexts on L20

astrai/inference/cache/buffer.py

@@ -27,7 +27,7 @@ class ReqToTokenPool:
         self.size = size
         self.max_context_len = max_context_len
         self.req_to_token = torch.zeros(
-            (size, max_context_len), dtype=torch.long, device=device
+            (size, max_context_len), dtype=torch.int32, device=device
         )
         self.free_slots = list(range(size))
         self._lock = threading.Lock()