tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : refactor model loader with backend registry (#10026)

Browse Source
This commit is contained in:
Diego Devesa
2024-10-30 02:01:23 +01:00
committed by GitHub
parent 8f275a7c45
commit c5b0f4b5d9
18 changed files with 1903 additions and 2019 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/compare-llama-bench.py
View File

@ -20,7 +20,7 @@ logger = logging.getLogger("compare-llama-bench")
# Properties by which to differentiate results per commit:
KEY_PROPERTIES = [
"cpu_info", "gpu_info", "n_gpu_layers", "cuda", "vulkan", "kompute", "metal", "sycl", "rpc", "gpu_blas",
"blas", "model_filename", "model_type", "model_size", "model_n_params", "n_batch", "n_ubatch", "embeddings", "n_threads",
"blas", "model_filename", "model_type", "n_batch", "n_ubatch", "embeddings", "n_threads",
"type_k", "type_v", "use_mmap", "no_kv_offload", "split_mode", "main_gpu", "tensor_split", "flash_attn", "n_prompt", "n_gen"
]