Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-15 03:08:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/release.yml
#	.github/workflows/ui-build-self-hosted.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui-publish.yml
#	.github/workflows/ui-self-hosted.yml
#	.github/workflows/ui.yml
#	.gitignore
#	README.md
#	docs/ops.md
#	docs/ops/Vulkan.csv
#	ggml/CMakeLists.txt
#	scripts/sync-ggml.last
#	scripts/sync_vendor.py
#	scripts/ui-assets.cmake
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
This commit is contained in:
Concedo
2026-06-14 11:26:16 +08:00
parent ef5a724ee4 c2ba3e47a2
commit ea0351c71a
117 changed files with 11026 additions and 2390 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+7
View File
@@ -2244,6 +2244,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.image_max_tokens = value;
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_IMAGE_MAX_TOKENS"));
add_opt(common_arg(
{"--mtmd-batch-max-tokens"}, "N",
string_format("maximum number of image tokens per batch when encoding images (default: %d)", params.mtmd_batch_max_tokens),
[](common_params & params, int value) {
params.mtmd_batch_max_tokens = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MTMD_BATCH_MAX_TOKENS"));
if (llama_supports_rpc()) {
add_opt(common_arg(
{"--rpc"}, "SERVERS",