Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/actions/windows-setup-rocm/action.yml
#	.github/workflows/build-cache.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/server.yml
#	ci/run.sh
#	docs/speculative.md
#	examples/lookup/lookup.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-et/ggml-et.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q4_0.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q8_0.cl
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-device.cpp
#	ggml/src/ggml-virtgpu/backend/shared/api_remoting.h
#	ggml/src/ggml-virtgpu/ggml-backend-buffer-type.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-device.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-device.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward.gen.h
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	tests/peg-parser/test-json-parser.cpp
#	tests/test-arg-parser.cpp
#	tests/test-backend-sampler.cpp
#	tests/test-sampling.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-08-11 15:13:15 +08:00
parent b39ff27d6f 153d324bcf
commit dcfe29317e
32 changed files with 813 additions and 385 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+32 -15
View File
@@ -206,11 +206,12 @@ extern "C" {
};
enum llama_load_mode {
LLAMA_LOAD_MODE_NONE = 0, // no special loading mode
LLAMA_LOAD_MODE_MMAP = 1, // memory map the model
LLAMA_LOAD_MODE_MLOCK = 2, // force system to keep model in RAM rather than swapping or compressing
LLAMA_LOAD_MODE_MMAP_MLOCK = 3, // mmap + force system to keep model in RAM rather than swapping or compressing
LLAMA_LOAD_MODE_DIRECT_IO = 4, // use direct I/O if available
LLAMA_LOAD_MODE_AUTO = -1, // auto-detect based on device capabilities
LLAMA_LOAD_MODE_NONE = 0, // no special loading mode
LLAMA_LOAD_MODE_MMAP = 1, // memory map the model
LLAMA_LOAD_MODE_MLOCK = 2, // force system to keep model in RAM rather than swapping or compressing
LLAMA_LOAD_MODE_MMAP_MLOCK = 3, // mmap + force system to keep model in RAM rather than swapping or compressing
LLAMA_LOAD_MODE_DIRECT_IO = 4, // use direct I/O if available
};
LLAMA_API const char * llama_load_mode_name(enum llama_load_mode load_mode);
@@ -351,14 +352,15 @@ extern "C" {
// NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations
// https://github.com/ggml-org/llama.cpp/pull/7544
struct llama_context_params {
uint32_t n_ctx; // text context, 0 = from model
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_rs_seq; // number of recurrent-state snapshots per seq for rollback (0 = no rollback) [EXPERIMENTAL]
uint32_t n_outputs_max; // max outputs in a ubatch (0 = n_batch)
int32_t n_threads; // number of threads to use for generation
int32_t n_threads_batch; // number of threads to use for batch processing
uint32_t n_ctx; // text context, 0 = from model
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_rs_seq; // number of recurrent-state snapshots per seq for rollback (0 = no rollback) [EXPERIMENTAL]
uint32_t n_outputs_max; // max outputs in a ubatch (0 = n_batch)
uint32_t n_outputs_max_per_seq; // max outputs per sequence (0 = n_outputs_max)
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_context_type ctx_type; // set the context type (e.g. MTP)
enum llama_rope_scaling_type rope_scaling_type; // RoPE scaling type, from `enum llama_rope_scaling_type`
@@ -1057,6 +1059,9 @@ extern "C" {
//
// Get the backend sampled token for the ith token.
// With multiple outputs, sampler state advances when the token is accepted,
// not when it is read through this function.
// When accepting multiple outputs, accept a contiguous prefix in output order.
// Returns LLAMA_TOKEN_NULL if no token was sampled.
LLAMA_API llama_token llama_get_sampled_token_ith(struct llama_context * ctx, int32_t i);
@@ -1273,9 +1278,12 @@ extern "C" {
// [EXPERIMENTAL]
// backend sampling interface:
// return true if the backend supports all ops needed by the sampler
// return true if the backend supports all ops needed by the sampler and can handle up to n_outputs_max_per_seq outputs per sequence
// note: call once per sampler
bool (*backend_init)(struct llama_sampler * smpl, ggml_backend_buffer_type_t buft);
bool (*backend_init)(
struct llama_sampler * smpl,
ggml_backend_buffer_type_t buft,
uint32_t n_outputs_max_per_seq);
// call after .backend_apply()
void (*backend_accept)(
@@ -1293,6 +1301,13 @@ extern "C" {
// called before graph execution to set inputs for the current ubatch
void (*backend_set_input)(struct llama_sampler * smpl);
// called before rebuilding a sampling graph to clear any internal sampler state
void (*backend_reset)(struct llama_sampler * smpl);
// copy mutable state from src into dst while keeping dst's references to the current sampling graph
// src and dst must have the same type and configuration
void (*copy_state)(const struct llama_sampler * src, struct llama_sampler * dst);
};
struct llama_sampler {
@@ -1313,6 +1328,7 @@ extern "C" {
LLAMA_API void llama_sampler_apply ( struct llama_sampler * smpl, llama_token_data_array * cur_p);
LLAMA_API void llama_sampler_reset ( struct llama_sampler * smpl);
LLAMA_API struct llama_sampler * llama_sampler_clone (const struct llama_sampler * smpl);
LLAMA_API void llama_sampler_copy (const struct llama_sampler * src, struct llama_sampler * dst);
// important: do not free if the sampler has been added to a llama_sampler_chain (via llama_sampler_chain_add)
LLAMA_API void llama_sampler_free ( struct llama_sampler * smpl);
@@ -1502,6 +1518,7 @@ extern "C" {
LLAMA_API uint32_t llama_sampler_get_seed(const struct llama_sampler * smpl);
/// @details Sample and accept a token from the idx-th output of the last evaluation
// For multiple outputs from one sampler, call this function in output order without gaps.
//
// Shorthand for:
// const auto * logits = llama_get_logits_ith(ctx, idx);