Remove llama_kv_cache_view due it was deleted on llama.cpp side too

rel: ggml-org/llama.cpp#13653

Author: serhii-nakon

llama_cpp/llama_cpp.py

@@ -1742,115 +1742,6 @@ def llama_apply_adapter_cvec(
 # //
 
 
-# // Information associated with an individual cell in the KV cache view.
-# struct llama_kv_cache_view_cell {
-#     // The position for this cell. Takes KV cache shifts into account.
-#     // May be negative if the cell is not populated.
-#     llama_pos pos;
-# };
-class llama_kv_cache_view_cell(ctypes.Structure):
-    """Information associated with an individual cell in the KV cache view.
-
-    Attributes:
-        pos (llama_pos): The position for this cell. Takes KV cache shifts into account.
-            May be negative if the cell is not populated."""
-
-    if TYPE_CHECKING:
-        pos: llama_pos
-
-    _fields_ = [("pos", llama_pos)]
-
-
-# // An updateable view of the KV cache.
-# struct llama_kv_cache_view {
-#     // Number of KV cache cells. This will be the same as the context size.
-#     int32_t n_cells;
-
-#     // Maximum number of sequences that can exist in a cell. It's not an error
-#     // if there are more sequences in a cell than this value, however they will
-#     // not be visible in the view cells_sequences.
-#     int32_t n_seq_max;
-
-#     // Number of tokens in the cache. For example, if there are two populated
-#     // cells, the first with 1 sequence id in it and the second with 2 sequence
-#     // ids then you'll have 3 tokens.
-#     int32_t token_count;
-
-#     // Number of populated cache cells.
-#     int32_t used_cells;
-
-#     // Maximum contiguous empty slots in the cache.
-#     int32_t max_contiguous;
-
-#     // Index to the start of the max_contiguous slot range. Can be negative
-#     // when cache is full.
-#     int32_t max_contiguous_idx;
-
-#     // Information for an individual cell.
-#     struct llama_kv_cache_view_cell * cells;
-
-
-#     // The sequences for each cell. There will be n_seq_max items per cell.
-#     llama_seq_id * cells_sequences;
-# };
-class llama_kv_cache_view(ctypes.Structure):
-    if TYPE_CHECKING:
-        n_cells: int
-        n_max_seq: int
-        token_count: int
-        used_cells: int
-        max_contiguous: int
-        max_contiguous_idx: int
-        cells: CtypesArray[llama_kv_cache_view_cell]
-        cells_sequences: CtypesArray[llama_seq_id]
-
-    _fields_ = [
-        ("n_cells", ctypes.c_int32),
-        ("n_max_seq", ctypes.c_int32),
-        ("token_count", ctypes.c_int32),
-        ("used_cells", ctypes.c_int32),
-        ("max_contiguous", ctypes.c_int32),
-        ("max_contiguous_idx", ctypes.c_int32),
-        ("cells", ctypes.POINTER(llama_kv_cache_view_cell)),
-        ("cells_sequences", ctypes.POINTER(llama_seq_id)),
-    ]
-
-
-llama_kv_cache_view_p = ctypes.POINTER(llama_kv_cache_view)
-
-
-# // Create an empty KV cache view. (use only for debugging purposes)
-# LLAMA_API struct llama_kv_cache_view llama_kv_cache_view_init(const struct llama_context * ctx, int32_t n_seq_max);
-@ctypes_function(
-    "llama_kv_cache_view_init",
-    [llama_context_p_ctypes, ctypes.c_int32],
-    llama_kv_cache_view,
-)
-def llama_kv_cache_view_init(
-    ctx: llama_context_p, n_seq_max: Union[ctypes.c_int32, int], /
-) -> llama_kv_cache_view:
-    """Create an empty KV cache view. (use only for debugging purposes)"""
-    ...
-
-
-# // Free a KV cache view. (use only for debugging purposes)
-# LLAMA_API void llama_kv_cache_view_free(struct llama_kv_cache_view * view);
-@ctypes_function("llama_kv_cache_view_free", [llama_kv_cache_view_p], None)
-def llama_kv_cache_view_free(view: "ctypes.pointer[llama_kv_cache_view]", /):  # type: ignore
-    """Free a KV cache view. (use only for debugging purposes)"""
-    ...
-
-
-# // Update the KV cache view structure with the current state of the KV cache. (use only for debugging purposes)
-# LLAMA_API void llama_kv_cache_view_update(const struct llama_context * ctx, struct llama_kv_cache_view * view);
-@ctypes_function(
-    "llama_kv_cache_view_update", [llama_context_p_ctypes, llama_kv_cache_view_p], None
-)
-def llama_kv_cache_view_update(ctx: llama_context_p, view: CtypesPointerOrRef[llama_kv_cache_view], /):  # type: ignore
-    """Update the KV cache view structure with the current state of the KV cache. (use only for debugging purposes)"""
-    ...
-
-
 # // Returns the number of tokens in the KV cache (slow, use only for debug)
 # // If a KV cell has multiple sequences assigned to it, it will be counted multiple times
 # LLAMA_API int32_t llama_kv_self_n_tokens(const struct llama_context * ctx);