vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 09:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/config.yml
#	.gitignore
#	CMakeLists.txt
#	CONTRIBUTING.md
#	Makefile
#	README.md
#	ci/run.sh
#	common/common.h
#	examples/main-cmake-pkg/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	models/ggml-vocab-bert-bge.gguf.inp
#	models/ggml-vocab-bert-bge.gguf.out
#	models/ggml-vocab-deepseek-coder.gguf.inp
#	models/ggml-vocab-deepseek-coder.gguf.out
#	models/ggml-vocab-deepseek-llm.gguf.inp
#	models/ggml-vocab-deepseek-llm.gguf.out
#	models/ggml-vocab-falcon.gguf.inp
#	models/ggml-vocab-falcon.gguf.out
#	models/ggml-vocab-gpt-2.gguf.inp
#	models/ggml-vocab-gpt-2.gguf.out
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	models/ggml-vocab-llama-spm.gguf.inp
#	models/ggml-vocab-llama-spm.gguf.out
#	models/ggml-vocab-mpt.gguf.inp
#	models/ggml-vocab-mpt.gguf.out
#	models/ggml-vocab-phi-3.gguf.inp
#	models/ggml-vocab-phi-3.gguf.out
#	models/ggml-vocab-starcoder.gguf.inp
#	models/ggml-vocab-starcoder.gguf.out
#	requirements.txt
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/check-requirements.sh
#	scripts/pod-llama.sh
#	src/CMakeLists.txt
#	src/llama.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo 2024-07-06 00:25:10 +08:00
commit 5b605d03ea
85 changed files with 4095 additions and 941 deletions
Download patch file Download diff file Expand all files Collapse all files

23
include/llama.h
View file

@ -89,6 +89,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_SMAUG = 14,
LLAMA_VOCAB_PRE_TYPE_PORO = 15,
LLAMA_VOCAB_PRE_TYPE_VIKING = 16,
LLAMA_VOCAB_PRE_TYPE_JAIS = 17,
};
// note: these values should be synchronized with ggml_rope
@ -179,6 +180,12 @@ extern "C" {
LLAMA_POOLING_TYPE_LAST = 3,
};
enum llama_attention_type {
LLAMA_ATTENTION_TYPE_UNSPECIFIED = -1,
LLAMA_ATTENTION_TYPE_CAUSAL = 0,
LLAMA_ATTENTION_TYPE_NON_CAUSAL = 1,
};
enum llama_split_mode {
LLAMA_SPLIT_MODE_NONE = 0, // single GPU
LLAMA_SPLIT_MODE_LAYER = 1, // split layers and KV across GPUs
@ -296,6 +303,7 @@ extern "C" {
enum llama_rope_scaling_type rope_scaling_type; // RoPE scaling type, from `enum llama_rope_scaling_type`
enum llama_pooling_type pooling_type; // whether to pool (sum) embedding results by sequence id
enum llama_attention_type attention_type; // attention type to use for embeddings
// ref: https://github.com/ggerganov/llama.cpp/pull/2054
float rope_freq_base; // RoPE base frequency, 0 = from model
@ -484,6 +492,13 @@ extern "C" {
// Get a llama model tensor
LLAMA_API struct ggml_tensor * llama_get_model_tensor(struct llama_model * model, const char * name);
// Returns true if the model contains an encoder that requires llama_encode() call
LLAMA_API bool llama_model_has_encoder(const struct llama_model * model);
// For encoder-decoder models, this function returns id of the token that must be provided
// to the decoder to start generating output sequence. For other models, it returns -1.
LLAMA_API llama_token llama_model_decoder_start_token(const struct llama_model * model);
// Returns 0 on success
LLAMA_API uint32_t llama_model_quantize(
const char * fname_inp,
@ -771,6 +786,14 @@ extern "C" {
// Frees a batch of tokens allocated with llama_batch_init()
LLAMA_API void llama_batch_free(struct llama_batch batch);
// Processes a batch of tokens with the ecoder part of the encoder-decoder model.
// Stores the encoder output internally for later use by the decoder cross-attention layers.
// 0 - success
// < 0 - error
LLAMA_API int32_t llama_encode(
struct llama_context * ctx,
struct llama_batch batch);
// Positive return values does not mean a fatal error, but rather a warning.
// 0 - success
// 1 - could not find a KV slot for the batch (try reducing the size of the batch or increase the context)