mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

ggml-virtgpu: improve the reliability of the code (#19846)

Browse Source 
* 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
This commit is contained in:
Kevin Pouget
2026-02-26 13:00:57 +01:00
committed by GitHub
parent efba35a860
commit ffaafde16f
30 changed files with 398 additions and 257 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-virtgpu/virtgpu-forward-buffer.cpp
+6 -6
View File
@@ -35,8 +35,8 @@ void apir_buffer_set_tensor(virtgpu * gpu,
apir_encode_ggml_tensor(encoder, tensor);
virtgpu_shmem temp_shmem; // Local storage for large buffers
virtgpu_shmem * shmem = &temp_shmem;
bool using_shared_shmem = false;
virtgpu_shmem * shmem = &temp_shmem;
bool using_shared_shmem = false;
if (size <= gpu->data_shmem.mmap_size) {
// Lock mutex before using shared data_shmem buffer
@@ -44,7 +44,7 @@ void apir_buffer_set_tensor(virtgpu * gpu,
GGML_ABORT(GGML_VIRTGPU "%s: Failed to lock data_shmem mutex", __func__);
}
using_shared_shmem = true;
shmem = &gpu->data_shmem;
shmem = &gpu->data_shmem;
} else if (virtgpu_shmem_create(gpu, size, shmem)) {
GGML_ABORT(GGML_VIRTGPU "%s: Couldn't allocate the guest-host shared buffer", __func__);
@@ -86,8 +86,8 @@ void apir_buffer_get_tensor(virtgpu * gpu,
apir_encode_ggml_tensor(encoder, tensor);
virtgpu_shmem temp_shmem; // Local storage for large buffers
virtgpu_shmem * shmem = &temp_shmem;
bool using_shared_shmem = false;
virtgpu_shmem * shmem = &temp_shmem;
bool using_shared_shmem = false;
if (size <= gpu->data_shmem.mmap_size) {
// Lock mutex before using shared data_shmem buffer
@@ -95,7 +95,7 @@ void apir_buffer_get_tensor(virtgpu * gpu,
GGML_ABORT(GGML_VIRTGPU "%s: Failed to lock data_shmem mutex", __func__);
}
using_shared_shmem = true;
shmem = &gpu->data_shmem;
shmem = &gpu->data_shmem;
} else if (virtgpu_shmem_create(gpu, size, shmem)) {
GGML_ABORT(GGML_VIRTGPU "%s: Couldn't allocate the guest-host shared buffer", __func__);