ggml-virtgpu: make the code thread safe (#19204)

* ggml-virtgpu: regenerate_remoting.py: add the ability to deprecate a function

* ggml-virtgpu: deprecate buffer_type is_host remoting

not necessary

* ggml-virtgpu: stop using static vars as cache

The static init isn't thread safe.

* ggml-virtgpu: protect the use of the shared memory to transfer data

* ggml-virtgpu: make the remote calls thread-safe

* ggml-virtgpu: backend: don't continue if couldn't allocate the tensor memory

* ggml-virtgpu: add a cleanup function for consistency

* ggml-virtgpu: backend: don't crash if buft->iface.get_max_size is missing

* fix style and ordering

* Remove the static variable in apir_device_get_count

* ggml-virtgpu: improve the logging

* fix review minor formatting changes
This commit is contained in:
Kevin Pouget
2026-02-04 03:46:18 +01:00
committed by GitHub
parent 2ceda3f662
commit 015deb9048
27 changed files with 397 additions and 237 deletions
+3 -3
View File
@@ -11,7 +11,7 @@
int32_t forward_flag = (int32_t) apir_command_type__; \
encoder_name = remote_call_prepare(gpu_dev_name, APIR_COMMAND_TYPE_FORWARD, forward_flag); \
if (!encoder_name) { \
GGML_ABORT("%s: failed to prepare the remote call encoder", __func__); \
GGML_ABORT(GGML_VIRTGPU "%s: failed to prepare the remote call encoder", __func__); \
} \
} while (0)
@@ -19,10 +19,10 @@
do { \
ret_name = (ApirForwardReturnCode) remote_call(gpu_dev_name, encoder_name, &decoder_name, 0, NULL); \
if (!decoder_name) { \
GGML_ABORT("%s: failed to kick the remote call", __func__); \
GGML_ABORT(GGML_VIRTGPU "%s: failed to kick the remote call", __func__); \
} \
if (ret_name < APIR_FORWARD_BASE_INDEX) { \
GGML_ABORT("%s: failed to forward the API call: %s: code %d", __func__, \
GGML_ABORT(GGML_VIRTGPU "%s: failed to forward the API call: %s: code %d", __func__, \
apir_forward_error(ret_name), ret_name); \
} \
ret_name = (ApirForwardReturnCode) (ret_name - APIR_FORWARD_BASE_INDEX); \