vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 09:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	common/common.cpp
#	common/common.h
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/infill/infill.cpp
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/rpc/README.md
#	examples/save-load-state/save-load-state.cpp
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-09-10 16:39:23 +08:00
commit a947558e0e
45 changed files with 2628 additions and 6743 deletions
Download patch file Download diff file Expand all files Collapse all files

11
include/llama.h
View file

@ -1129,15 +1129,16 @@ extern "C" {
int32_t n_logit_bias,
const llama_logit_bias * logit_bias);
// Shorthand for:
/// @details Sample and accept a token from the idx-th output of the last evaluation
//
// Shorthand for:
// const auto * logits = llama_get_logits_ith(ctx, idx);
// llama_token_data_array cur_p = { ... init from logits ... };
// llama_sampler_apply(smpl, &cur_p);
// return cur_p.data[cur_p.selected].id;
//
// At this point, this is mostly a convenience function.
//
// auto token = cur_p.data[cur_p.selected].id;
// llama_sampler_accept(smpl, token);
// return token;
// Returns the sampled token
LLAMA_API llama_token llama_sampler_sample(struct llama_sampler * smpl, struct llama_context * ctx, int32_t idx);
// TODO: extend in the future