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 commit '11b068d06605288ce7917534b46d52b47823dc13' into concedo_experimental

Browse Source 
# Conflicts:
#	CONTRIBUTING.md
#	docs/backend/SYCL.md
#	docs/install.md
#	docs/speculative.md
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/glu.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-07-31 17:06:19 +08:00
parent 49ff71991e 11b068d066
commit 98926f27c1
81 changed files with 5314 additions and 518 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.h
+13 -5
View File
@@ -174,6 +174,7 @@ enum common_speculative_type {
COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, // Eagle3 speculative decoding
COMMON_SPECULATIVE_TYPE_DRAFT_MTP, // Multi-token prediction
COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, // DFlash speculative decoding
COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, // DSpark speculative decoding (DFlash + Markov head)
COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE, // simple self-speculative decoding based on n-grams
COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K, // self-speculative decoding with n-gram keys only
COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V, // self-speculative decoding with n-gram keys and 4 m-gram values
@@ -389,7 +390,7 @@ struct common_params_speculative {
uint32_t need_n_rs_seq() const {
bool needs_rs_seq = std::any_of(types.begin(), types.end(), [&](auto t) {
return t == COMMON_SPECULATIVE_TYPE_DRAFT_MTP || t == COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3 || t == COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH;
return t == COMMON_SPECULATIVE_TYPE_DRAFT_MTP || t == COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3 || t == COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH || t == COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK;
});
return needs_rs_seq ? draft.n_max : 0u;
@@ -949,10 +950,17 @@ enum common_context_seq_rm_type {
// note: clears the memory of the context
common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx);
// aborts execution on failure
void common_context_seq_rm (llama_context * ctx, llama_seq_id seq_id, llama_pos p0, llama_pos p1);
void common_context_seq_add(llama_context * ctx, llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos delta);
void common_context_seq_cp (llama_context * ctx, llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1);
struct common_memory {
llama_context * ctx_tgt = nullptr;
llama_context * ctx_dft = nullptr;
void init(llama_context * ctx_tgt, llama_context * ctx_dft = nullptr);
// aborts execution on failure
void seq_rm (llama_seq_id seq_id, llama_pos p0, llama_pos p1) const;
void seq_add(llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos delta) const;
void seq_cp (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) const;
};
//
// Batch utils