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

add --no-mmap in llama-bench (#5257)

Browse source 
* add --no-mmap, show sycl backend

* fix conflict

* fix code format, change print for --no-mmap

* ren no_mmap to mmap, show mmap when not default value in printer

* update guide for mmap

* mv position to reduce model reload
This commit is contained in:
Neo Zhang Jianyu 2024-02-02 03:48:53 +08:00 • committed by GitHub
parent 4d0924a890
commit 128dcbd3c9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 89 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-sycl.h
View file

@ -22,7 +22,8 @@ GGML_API ggml_backend_t ggml_backend_sycl_init(int device);
GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device);
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);
#ifdef __cplusplus
}
#endif