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/docker.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	flake.lock
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-05-28 21:57:19 +08:00
commit 4ed9ba7352
58 changed files with 2404 additions and 361 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama.h
View file

@ -85,6 +85,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_QWEN2 = 11,
LLAMA_VOCAB_PRE_TYPE_OLMO = 12,
LLAMA_VOCAB_PRE_TYPE_DBRX = 13,
LLAMA_VOCAB_PRE_TYPE_SMAUG = 14,
};
// note: these values should be synchronized with ggml_rope
@ -264,6 +265,8 @@ extern "C" {
bool check_tensors; // validate model tensor data
};
// NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations
// https://github.com/ggerganov/llama.cpp/pull/7544
struct llama_context_params {
uint32_t seed; // RNG seed, -1 for random
uint32_t n_ctx; // text context, 0 = from model
@ -290,14 +293,14 @@ extern "C" {
ggml_backend_sched_eval_callback cb_eval;
void * cb_eval_user_data;
enum ggml_type type_k; // data type for K cache
enum ggml_type type_v; // data type for V cache
enum ggml_type type_k; // data type for K cache [EXPERIMENTAL]
enum ggml_type type_v; // data type for V cache [EXPERIMENTAL]
// Keep the booleans together to avoid misalignment during copy-by-value.
bool logits_all; // the llama_decode() call computes all logits, not just the last one (DEPRECATED - set llama_batch.logits instead)
bool embeddings; // if true, extract embeddings (together with logits)
bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU
bool flash_attn; // whether to use flash attention
bool flash_attn; // whether to use flash attention [EXPERIMENTAL]
// Abort callback
// if it returns true, execution of llama_decode() will be aborted
@ -825,6 +828,9 @@ extern "C" {
// Check if the token is supposed to end generation (end-of-generation, eg. EOS, EOT, etc.)
LLAMA_API bool llama_token_is_eog(const struct llama_model * model, llama_token token);
// Identify if Token Id is a control token or a render-able token
LLAMA_API bool llama_token_is_control(const struct llama_model * model, llama_token token);
// Special tokens
LLAMA_API llama_token llama_token_bos(const struct llama_model * model); // beginning-of-sentence
LLAMA_API llama_token llama_token_eos(const struct llama_model * model); // end-of-sentence