Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/intel.Dockerfile
#	README.md
#	docs/backend/SYCL.md
#	docs/install.md
#	docs/ops.md
#	docs/ops/SYCL.csv
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/concat.cpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/element_wise.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/mmvq.hpp
#	tests/peg-parser/test-gbnf-generation.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo
2026-06-16 17:55:04 +08:00
parent 05dbd9a195 a1824902b5
commit 382ce55fb7
18 changed files with 413 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/bench/bench.py
+3
View File
@@ -40,6 +40,7 @@ def main(args_in: list[str] | None = None) -> None:
required=True)
parser.add_argument("--hf-repo", type=str, help="Hugging Face model repository", required=True)
parser.add_argument("--hf-file", type=str, help="Hugging Face model file", required=True)
parser.add_argument("--offline", action="store_true", default=False, help="Offline mode: forces use of cache, prevents network access")
parser.add_argument("-ngl", "--n-gpu-layers", type=int, help="layers to the GPU for computation", required=True)
parser.add_argument("--ctx-size", type=int, help="Set the size of the prompt context", required=True)
parser.add_argument("--parallel", type=int, help="Set the number of slots for process requests", required=True)
@@ -268,6 +269,8 @@ def start_server_background(args):
]
server_args.extend(['--hf-repo', args.hf_repo])
server_args.extend(['--hf-file', args.hf_file])
if args.offline:
server_args.append('--offline')
server_args.extend(['--n-gpu-layers', args.n_gpu_layers])
server_args.extend(['--ctx-size', args.ctx_size])
server_args.extend(['--parallel', args.parallel])