vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-17 04:09:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

fix: CUDA device PCI bus ID de-dupe OOMing (ignoring other 3 gpus entirely) (#22533)

Browse source 
* fix: CUDA device PCI bus ID detection for multi-GPU de-dupe

* HIP, MUSA macros

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
lucy 2026-05-02 16:19:25 -04:00 • committed by GitHub
parent 0754b7b6fe
commit d05fe1d7da
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/src/ggml-cuda/ggml-cuda.cu
View file

@ -5431,8 +5431,8 @@ ggml_backend_reg_t ggml_backend_cuda_reg() {
CUDA_CHECK(cudaGetDeviceProperties(&prop, i));
dev_ctx->description = prop.name;
char pci_bus_id[16] = {};
snprintf(pci_bus_id, sizeof(pci_bus_id), "%04x:%02x:%02x.0", prop.pciDomainID, prop.pciBusID, prop.pciDeviceID);
char pci_bus_id[32] = {};
CUDA_CHECK(cudaDeviceGetPCIBusId(pci_bus_id, sizeof(pci_bus_id), i));
dev_ctx->pci_bus_id = pci_bus_id;
dev_ctx->op_offload_min_batch_size = min_batch_size;

1
ggml/src/ggml-cuda/vendors/hip.h vendored
View file

@ -55,6 +55,7 @@
#define cudaDeviceDisablePeerAccess hipDeviceDisablePeerAccess
#define cudaDeviceEnablePeerAccess hipDeviceEnablePeerAccess
#define cudaDeviceGetAttribute hipDeviceGetAttribute
#define cudaDeviceGetPCIBusId hipDeviceGetPCIBusId
#define cudaDeviceProp hipDeviceProp_t
#define cudaDeviceSynchronize hipDeviceSynchronize
#define cudaError_t hipError_t

1
ggml/src/ggml-cuda/vendors/musa.h vendored
View file

@ -39,6 +39,7 @@
#define cudaDeviceCanAccessPeer musaDeviceCanAccessPeer
#define cudaDeviceDisablePeerAccess musaDeviceDisablePeerAccess
#define cudaDeviceEnablePeerAccess musaDeviceEnablePeerAccess
#define cudaDeviceGetPCIBusId musaDeviceGetPCIBusId
#define cudaDeviceProp musaDeviceProp
#define cudaDeviceSynchronize musaDeviceSynchronize
#define cudaError_t musaError_t