vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '8c570c9496' into concedo_experimental

Browse source 
# Conflicts:
#	README.md
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-05-10 16:55:26 +08:00
commit db82bad6f2
18 changed files with 45581 additions and 35766 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama.cpp
View file

@ -12779,7 +12779,7 @@ struct llm_tokenizer_wpm {
continue;
}
code = unicode_tolower(code);
if (type == CODEPOINT_TYPE_WHITESPACE) {
if (type == CODEPOINT_TYPE_SEPARATOR) {
code = ' ';
}
std::string s = unicode_cpt_to_utf8(code);
@ -15824,13 +15824,6 @@ struct llama_context * llama_new_context_with_model(
cparams.flash_attn = false;
}
#ifdef GGML_USE_HIPBLAS
if (cparams.flash_attn) {
LLAMA_LOG_WARN("%s: flash_attn is not yet compatible with HIPBLAS builds - forcing off\n", __func__);
cparams.flash_attn = false;
}
#endif
if (params.seed == LLAMA_DEFAULT_SEED) {
params.seed = time(NULL);
}
@ -18199,7 +18192,7 @@ struct llama_timings llama_get_timings(struct llama_context * ctx) {
/*.t_eval_ms =*/ 1e-3 * ctx->t_eval_us,
/*.n_sample =*/ std::max(1, ctx->n_sample),
/*.n_p_eval =*/ std::max(1, ctx->n_p_eval),
/*.n_p_eval =*/ std::max(0, ctx->n_p_eval),
/*.n_eval =*/ std::max(1, ctx->n_eval),
};