sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 114 Packages Projects Releases Wiki Activity

llama: end-to-end tests (#19802)

Browse Source 
* tests: add end-to-end tests per model architecture

* fixup for rebase

* fix use-after-free in llama-model-loader.cpp

* fix CI

* fix WebGPU

* fix CI

* disable CI for macOS-latest-cmake-arm64

* use expert_weights_scale only if != 0.0f

* comments
This commit is contained in:
Johannes Gäßler
2026-03-08 12:30:21 +01:00
committed by GitHub
parent a95047979a
commit a976ff081b
33 changed files with 1607 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+8 -1
View File
@@ -2666,7 +2666,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, const std::string & value) {
params.out_file = value;
}
).set_examples({LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_CVECTOR_GENERATOR, LLAMA_EXAMPLE_EXPORT_LORA, LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_FINETUNE}));
).set_examples({LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_CVECTOR_GENERATOR, LLAMA_EXAMPLE_EXPORT_LORA, LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_FINETUNE, LLAMA_EXAMPLE_RESULTS}));
add_opt(common_arg(
{"-ofreq", "--output-frequency"}, "N",
string_format("output the imatrix every N iterations (default: %d)", params.n_out_freq),
@@ -3607,6 +3607,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
).set_examples({ LLAMA_EXAMPLE_FINETUNE }));
add_opt(common_arg(
{"--check"},
string_format("check rather than generate results (default: %s)", params.check ? "true" : "false"),
[](common_params & params) {
params.check = true;
}
).set_examples({LLAMA_EXAMPLE_RESULTS}));
add_opt(common_arg(
{"--save-logits"},
string_format("save final logits to files for verification (default: %s)", params.save_logits ? "true" : "false"),
common/common.h
+3
View File
@@ -104,6 +104,7 @@ enum llama_example {
LLAMA_EXAMPLE_DIFFUSION,
LLAMA_EXAMPLE_FINETUNE,
LLAMA_EXAMPLE_FIT_PARAMS,
LLAMA_EXAMPLE_RESULTS,
LLAMA_EXAMPLE_COUNT,
};
@@ -456,6 +457,8 @@ struct common_params {
bool kl_divergence = false; // compute KL divergence
bool check = false; // check rather than generate results for llama-results
bool usage = false; // print usage
bool completion = false; // print source-able completion script
bool use_color = false; // use color to distinguish generations and inputs