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 branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	README.md
#	ci/run.sh
#	llama.cpp
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	requirements.txt
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-tokenizer-1-bpe.cpp
This commit is contained in:
Concedo 2024-05-14 19:28:47 +08:00
commit 2ee808a747
66 changed files with 3034 additions and 1821 deletions
Download patch file Download diff file Expand all files Collapse all files

6
common/sampling.cpp
View file

@ -35,7 +35,7 @@ struct llama_sampling_context * llama_sampling_init(const struct llama_sampling_
result->prev.resize(params.n_prev);
result->n_considered = 0;
result->n_valid = 0;
llama_sampling_set_rng_seed(result, params.seed);
@ -66,7 +66,7 @@ void llama_sampling_reset(llama_sampling_context * ctx) {
std::fill(ctx->prev.begin(), ctx->prev.end(), 0);
ctx->cur.clear();
ctx->n_considered = 0;
ctx->n_valid = 0;
}
void llama_sampling_set_rng_seed(struct llama_sampling_context * ctx, uint32_t seed) {
@ -256,7 +256,7 @@ static llama_token llama_sampling_sample_impl(
}
}
ctx_sampling->n_considered = cur_p.size;
ctx_sampling->n_valid = temp == 0.0f ? 0 : cur_p.size;
return id;
}