refactor kvcache allocate and reshape

  * Unify the kvcache tensor initialization logic of deepseek and normal models
  * spilt initialize_kv_cache_tensors into _allocate_kv_cache_tensors and _reshape_kv_cache_tensors, following gpu modelrunner in vllm
  * Fix the shared_by logic so that the same attention spec could share the same buffer instead of allocating more hbm.

Signed-off-by: MengqingCao <[email protected]>

Author: MengqingCao