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 branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/python-type-check.yml
#	CMakeLists.txt
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	examples/embedding/embedding.cpp
#	examples/server/README.md
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/ggml.c
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/sync-ggml.last
#	src/llama-vocab.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-tokenizer-0.cpp
This commit is contained in:
Concedo 2024-10-02 01:00:57 +08:00
commit ce7f9c9a2c
39 changed files with 103400 additions and 102738 deletions
Download patch file Download diff file Expand all files Collapse all files

13
include/llama.h
View file

@ -102,6 +102,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_BLOOM = 23,
LLAMA_VOCAB_PRE_TYPE_GPT3_FINNISH = 24,
LLAMA_VOCAB_PRE_TYPE_EXAONE = 25,
LLAMA_VOCAB_PRE_TYPE_CHAMELEON = 26,
};
enum llama_rope_type {
@ -192,6 +193,7 @@ extern "C" {
LLAMA_POOLING_TYPE_MEAN = 1,
LLAMA_POOLING_TYPE_CLS = 2,
LLAMA_POOLING_TYPE_LAST = 3,
LLAMA_POOLING_TYPE_RANK = 4, // used by reranking models to attach the classification head to the graph
};
enum llama_attention_type {
@ -201,9 +203,9 @@ extern "C" {
};
enum llama_split_mode {
LLAMA_SPLIT_MODE_NONE = 0, // single GPU
LLAMA_SPLIT_MODE_LAYER = 1, // split layers and KV across GPUs
LLAMA_SPLIT_MODE_ROW = 2, // split rows across GPUs
LLAMA_SPLIT_MODE_NONE = 0, // single GPU
LLAMA_SPLIT_MODE_LAYER = 1, // split layers and KV across GPUs
LLAMA_SPLIT_MODE_ROW = 2, // split rows across GPUs
};
// TODO: simplify (https://github.com/ggerganov/llama.cpp/pull/9294#pullrequestreview-2286561979)
@ -873,7 +875,8 @@ extern "C" {
// Get the embeddings for a sequence id
// Returns NULL if pooling_type is LLAMA_POOLING_TYPE_NONE
// shape: [n_embd] (1-dimensional)
// when pooling_type == LLAMA_POOLING_TYPE_RANK, returns float[1] with the rank of the sequence
// otherwise: float[n_embd] (1-dimensional)
LLAMA_API float * llama_get_embeddings_seq(struct llama_context * ctx, llama_seq_id seq_id);
//
@ -912,6 +915,8 @@ extern "C" {
//
// Tokenization
//
// The API is thread-safe.
//
/// @details Convert the provided text into tokens.
/// @param tokens The tokens pointer must be large enough to hold the resulting tokens.