mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-11-02 17:17:57 +01:00
Kevin Pouget
ffaafde16f
* ggml-virtgpu-backend: validate the consistency of the received objects This patch adds consistency checks in the ggml-virtgpu-backend (running on the host side) to ensure that the data received from the guest is consistent (valid pointers, valid sizes and offsets). * ggml-virtgpu-backend: add fallback/skips for optional ggml backend methods ``` 1. bck->iface.synchronize(bck) 2. buft->iface.get_alloc_size(buft, op) 3. buft->iface.get_max_size(buft) ``` these three methods are optional in the GGML interface. `get_max_size` was already properly defaulted, but `backend sychronize` and `butf get_max_size` would have segfaulted the backend if not implemented. * ggml-virtgpu-backend: fix log format missing argument * ggml-virtgpu-backend: improve the abort message * ggml-virtgpu-backend: more safety checks * ggml-virtgpu-backend: new error code * ggml-virtgpu-backend: initialize all the error codes * ggml-virtgpu: add a missing comment generated by the code generator * ggml-virtgpu: add the '[virtgpu]' prefix to the device/buffer names * ggml-virtgpu: apir_device_buffer_from_ptr: improve the error message * ggml-virtgpu: shared: make it match the latest api_remoting.h of Virglrenderer APIR (still unmerged) * ggml-virtgpu: update the code generator to have dispatch_command_name in a host/guest shared file * ggml-virtgpu: REMOTE_CALL: fail if the backend returns an error * docs/backend/VirtGPU.md: indicate that the RAM+VRAM size is limed to 64 GB with libkrun * ggml-virtgpu: turn off clang-format header ordering for some of the files Compilation breaks when ordered alphabetically. * ggml-virtgpu: clang-format * ggml-virtgpu/backend/shared/api_remoting: better comments for the APIR return codes
74 lines
4.5 KiB
C
74 lines
4.5 KiB
C
#pragma once
|
|
|
|
/* device */
|
|
uint32_t backend_device_get_device_count(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_count(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_name(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_description(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_type(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_memory(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_supports_op(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_buffer_type(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_get_props(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_device_buffer_from_ptr(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
|
|
/* buffer-type */
|
|
uint32_t backend_buffer_type_get_name(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_type_get_alignment(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_type_get_max_size(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_IS_HOST is deprecated. Keeping the handler for backward compatibility. */
|
|
uint32_t backend_buffer_type_is_host(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_type_alloc_buffer(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_type_get_alloc_size(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
|
|
/* buffer */
|
|
uint32_t backend_buffer_get_base(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_set_tensor(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_get_tensor(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_cpy_tensor(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_clear(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
uint32_t backend_buffer_free_buffer(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
|
|
/* backend */
|
|
uint32_t backend_backend_graph_compute(apir_encoder * enc, apir_decoder * dec, virgl_apir_context * ctx);
|
|
|
|
extern "C" {
|
|
static const backend_dispatch_t apir_backend_dispatch_table[APIR_BACKEND_DISPATCH_TABLE_COUNT] = {
|
|
|
|
/* device */
|
|
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_DEVICE_COUNT = */ backend_device_get_device_count,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_COUNT = */ backend_device_get_count,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_NAME = */ backend_device_get_name,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_DESCRIPTION = */ backend_device_get_description,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_TYPE = */ backend_device_get_type,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_MEMORY = */ backend_device_get_memory,
|
|
/* APIR_COMMAND_TYPE_DEVICE_SUPPORTS_OP = */ backend_device_supports_op,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_BUFFER_TYPE = */ backend_device_get_buffer_type,
|
|
/* APIR_COMMAND_TYPE_DEVICE_GET_PROPS = */ backend_device_get_props,
|
|
/* APIR_COMMAND_TYPE_DEVICE_BUFFER_FROM_PTR = */ backend_device_buffer_from_ptr,
|
|
|
|
/* buffer-type */
|
|
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_GET_NAME = */ backend_buffer_type_get_name,
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_GET_ALIGNMENT = */ backend_buffer_type_get_alignment,
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_GET_MAX_SIZE = */ backend_buffer_type_get_max_size,
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_IS_HOST = */ backend_buffer_type_is_host /* DEPRECATED */,
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_ALLOC_BUFFER = */ backend_buffer_type_alloc_buffer,
|
|
/* APIR_COMMAND_TYPE_BUFFER_TYPE_GET_ALLOC_SIZE = */ backend_buffer_type_get_alloc_size,
|
|
|
|
/* buffer */
|
|
|
|
/* APIR_COMMAND_TYPE_BUFFER_GET_BASE = */ backend_buffer_get_base,
|
|
/* APIR_COMMAND_TYPE_BUFFER_SET_TENSOR = */ backend_buffer_set_tensor,
|
|
/* APIR_COMMAND_TYPE_BUFFER_GET_TENSOR = */ backend_buffer_get_tensor,
|
|
/* APIR_COMMAND_TYPE_BUFFER_CPY_TENSOR = */ backend_buffer_cpy_tensor,
|
|
/* APIR_COMMAND_TYPE_BUFFER_CLEAR = */ backend_buffer_clear,
|
|
/* APIR_COMMAND_TYPE_BUFFER_FREE_BUFFER = */ backend_buffer_free_buffer,
|
|
|
|
/* backend */
|
|
|
|
/* APIR_COMMAND_TYPE_BACKEND_GRAPH_COMPUTE = */ backend_backend_graph_compute,
|
|
};
|
|
}
|