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-cuda.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	.github/workflows/docker.yml
#	docs/docker.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/CMakeLists.txt
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo 2024-08-30 10:37:39 +08:00
commit d220495dd4
42 changed files with 100585 additions and 99448 deletions
Download patch file Download diff file Expand all files Collapse all files

17
include/llama.h
View file

@ -304,8 +304,8 @@ extern "C" {
uint32_t n_batch; // logical maximum batch size that can be submitted to llama_decode
uint32_t n_ubatch; // physical maximum batch size
uint32_t n_seq_max; // max number of sequences (i.e. distinct states for recurrent models)
uint32_t n_threads; // number of threads to use for generation
uint32_t n_threads_batch; // number of threads to use for batch processing
int32_t n_threads; // number of threads to use for generation
int32_t n_threads_batch; // number of threads to use for batch processing
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
@ -428,6 +428,13 @@ extern "C" {
//optional:
LLAMA_API void llama_numa_init(enum ggml_numa_strategy numa);
// Optional: an auto threadpool gets created in ggml if not passed explicitly
LLAMA_API void llama_attach_threadpool(
struct llama_context * ctx,
ggml_threadpool_t threadpool,
ggml_threadpool_t threadpool_batch);
LLAMA_API void llama_detach_threadpool(struct llama_context * ctx);
// Call once at the end of the program - currently only used for MPI
LLAMA_API void llama_backend_free(void);
@ -839,13 +846,13 @@ extern "C" {
// Set the number of threads used for decoding
// n_threads is the number of threads used for generation (single token)
// n_threads_batch is the number of threads used for prompt and batch processing (multiple tokens)
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch);
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, int32_t n_threads, int32_t n_threads_batch);
// Get the number of threads used for generation of a single token.
LLAMA_API uint32_t llama_n_threads(struct llama_context * ctx);
LLAMA_API int32_t llama_n_threads(struct llama_context * ctx);
// Get the number of threads used for prompt and batch processing (multiple token).
LLAMA_API uint32_t llama_n_threads_batch(struct llama_context * ctx);
LLAMA_API int32_t llama_n_threads_batch(struct llama_context * ctx);
// Set whether the model is in embeddings mode or not
// If true, embeddings will be returned but logits will not