nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 33 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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 10:46:18 +08:00
committed by GitHub
parent 2ceda3f662
commit 015deb9048
27 changed files with 397 additions and 237 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-virtgpu/backend/backend-dispatched-device.cpp
+1 -1
View File
@@ -124,7 +124,7 @@ uint32_t backend_device_buffer_from_ptr(apir_encoder * enc, apir_decoder * dec,
void * shmem_ptr = ctx->iface->get_shmem_ptr(ctx->ctx_id, shmem_res_id);
if (!shmem_ptr) {
GGML_LOG_ERROR("Couldn't get the shmem addr from virgl\n");
GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: Couldn't get the shmem addr from virgl\n", __func__);
apir_decoder_set_fatal(dec);
return 1;
}