vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit 'ad3a0505e3' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/code-coverage.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/server.yml
#	.github/workflows/zig-build.yml
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	README-sycl.md
#	README.md
#	build.zig
#	common/CMakeLists.txt
#	llama.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-04-06 18:32:57 +08:00
commit 9c0fbf9f73
67 changed files with 10861 additions and 4661 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/speculative/speculative.cpp
View file

@ -221,7 +221,8 @@ int main(int argc, char ** argv) {
if (params.sparams.temp > 0) {
// stochastic verification
llama_token_data_array dist_tgt = llama_sampling_probability_distribution(ctx_sampling, ctx_tgt, NULL, drafts[s_keep].i_batch_tgt[i_dft]);
llama_token_data_array dist_tgt = llama_sampling_prepare(ctx_sampling, ctx_tgt, NULL, drafts[s_keep].i_batch_tgt[i_dft], true, NULL);
llama_sample_softmax(ctx_tgt, &dist_tgt);
float p_tgt = 0, p_dft = 0;
// GGML_ASSERT(dist_tgt.size() == dist_dft.size());