vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 02:19:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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

8
common/sampling.h
View file

@ -132,12 +132,14 @@ llama_token llama_sampling_sample(
struct llama_context * ctx_cfg,
int idx = 0);
// returns the probability that token of given id will be sampled
llama_token_data_array llama_sampling_probability_distribution(
// Prepares and adjusts the set of token candidates for sampling based on penalties, biases, and sampling parameters.
llama_token_data_array llama_sampling_prepare(
struct llama_sampling_context * ctx_sampling,
struct llama_context * ctx_main,
struct llama_context * ctx_cfg,
int idx = 0);
int idx = 0,
bool apply_grammar = true,
std::vector<float> * original_logits = nullptr);
void llama_sampling_accept(
struct llama_sampling_context * ctx_sampling,