vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Support multiple GPUs (split mode) on SYCL backend (#5806)

Browse source 
* suport multiple cards: split-mode - layer|row

* rm warning

* rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test

* update news

* fix merge error

* update according to review comments
This commit is contained in:
Neo Zhang Jianyu 2024-03-02 19:49:30 +08:00 • committed by GitHub
parent 9bf297a02b
commit 715641391d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 1506 additions and 814 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml-sycl.h
View file

@ -24,6 +24,11 @@ GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_host_buffer_type(void);
GGML_API void ggml_backend_sycl_print_sycl_devices(void);
GGML_API GGML_CALL void ggml_sycl_get_gpu_list(int *id_list, int max_len);
GGML_API GGML_CALL void ggml_sycl_get_device_description(int device, char *description, size_t description_size);
GGML_API GGML_CALL int ggml_backend_sycl_get_device_count();
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
GGML_API GGML_CALL void ggml_backend_sycl_get_device_memory(int device, size_t *free, size_t *total);
GGML_API GGML_CALL int ggml_backend_sycl_get_device_index(int device_id);
#ifdef __cplusplus
}
#endif