tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add asserts for type conversion in fattn kernels (#9971)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-10-21 16:20:46 +03:00
committed by GitHub
parent d5ebd79c76
commit f594bc80ba
3 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/common.cpp
View File

@ -1035,7 +1035,7 @@ static ggml_type kv_cache_type_from_str(const std::string & s) {
return GGML_TYPE_Q5_1;
}
throw std::runtime_error("Invalid cache type: " + s);
throw std::runtime_error("Unsupported cache type: " + s);
}
struct llama_context_params common_context_params_to_llama(const common_params & params) {
@ -1047,7 +1047,7 @@ struct llama_context_params common_context_params_to_llama(const common_params &
cparams.n_ubatch = params.n_ubatch;
cparams.n_threads = params.cpuparams.n_threads;
cparams.n_threads_batch = params.cpuparams_batch.n_threads == -1 ?
params.cpuparams.n_threads : params.cpuparams_batch.n_threads;
params.cpuparams.n_threads : params.cpuparams_batch.n_threads;
cparams.logits_all = params.logits_all;
cparams.embeddings = params.embedding;
cparams.rope_scaling_type = params.rope_scaling_type;