Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/nix/package.nix
#	.github/labeler.yml
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	Package.swift
#	README.md
#	ci/run.sh
#	docs/build.md
#	examples/CMakeLists.txt
#	flake.lock
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	grammars/README.md
#	requirements/requirements-convert_hf_to_gguf.txt
#	requirements/requirements-convert_hf_to_gguf_update.txt
#	scripts/check-requirements.sh
#	scripts/compare-llama-bench.py
#	scripts/gen-unicode-data.py
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	scripts/sync-ggml.sh
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-tokenizer-random.py
This commit is contained in:
Concedo
2024-07-11 16:36:16 +08:00
parent eeecaf442a a977c11544
commit 2cad736260
85 changed files with 12568 additions and 445 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/sampling.cpp
+6 -5
View File
@@ -282,8 +282,6 @@ static llama_token llama_sampling_sample_impl(
GGML_ASSERT(!original_logits.empty());
}
llama_token id = 0;
// Get a pointer to the logits
float * logits = llama_get_logits_ith(ctx_main, idx);
if (temp < 0.0) {
// greedy sampling, with probs
@@ -324,6 +322,9 @@ static llama_token llama_sampling_sample_impl(
}
if (ctx_sampling->grammar != NULL && !is_resampling) {
// Get a pointer to the logits
float * logits = llama_get_logits_ith(ctx_main, idx);
// Create an array with a single token data element for the sampled id
llama_token_data single_token_data = {id, logits[id], 0.0f};
llama_token_data_array single_token_data_array = { &single_token_data, 1, false };
@@ -377,7 +378,7 @@ static llama_token_data_array llama_sampling_prepare_impl(
if (ctx_sampling->grammar != NULL && !apply_grammar) {
GGML_ASSERT(original_logits != NULL);
// Only make a copy of the original logits if we are not applying grammar checks, not sure if I actually have to do this.
*original_logits = {logits, logits + llama_n_vocab(llama_get_model(ctx_main))};
*original_logits = {logits, logits + n_vocab};
}
// apply params.logit_bias map
@@ -390,10 +391,10 @@ static llama_token_data_array llama_sampling_prepare_impl(
llama_sample_apply_guidance(ctx_main, logits, logits_guidance, params.cfg_scale);
}
cur.clear();
cur.resize(n_vocab);
for (llama_token token_id = 0; token_id < n_vocab; token_id++) {
cur.emplace_back(llama_token_data{token_id, logits[token_id], 0.0f});
cur[token_id] = llama_token_data{token_id, logits[token_id], 0.0f};
}
llama_token_data_array cur_p = { cur.data(), cur.size(), false };