vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-11 21:32:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	common/common.cpp
#	examples/batched/README.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/arch-fallback.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/sync-ggml.last
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo 2025-11-25 16:38:07 +08:00
commit 724763fdec
55 changed files with 5248 additions and 3753 deletions
Download patch file Download diff file Expand all files Collapse all files

47
src/llama-model.cpp
View file

@ -107,6 +107,7 @@
#include "models/qwen3vl-moe.cpp"
#include "models/qwen3moe.cpp"
#include "models/refact.cpp"
#include "models/rnd1.cpp"
#include "models/rwkv6-base.cpp"
#include "models/rwkv6.cpp"
#include "models/rwkv6qwen2.cpp"
@ -1138,6 +1139,18 @@ void llama_model::load_hparams(llama_model_loader & ml) {
default: type = LLM_TYPE_UNKNOWN;
}
} break;
case LLM_ARCH_RND1:
{
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false);
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 48: type = LLM_TYPE_30B_A3B; break;
default: type = LLM_TYPE_UNKNOWN;
}
// Set non-causal attention for diffusion models
hparams.causal_attn = false;
} break;
case LLM_ARCH_QWEN2MOE:
{
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false);
@ -1695,7 +1708,8 @@ void llama_model::load_hparams(llama_model_loader & ml) {
} break;
case LLM_ARCH_DEEPSEEK2:
{
bool is_lite = (hparams.n_layer == 27);
// lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B
bool is_lite = (hparams.n_layer == 27 || hparams.n_layer == 26);
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead);
if (!is_lite) {
@ -3556,6 +3570,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
} break;
case LLM_ARCH_QWEN3MOE:
case LLM_ARCH_QWEN3VLMOE:
case LLM_ARCH_RND1:
{
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
@ -4736,7 +4751,8 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
} break;
case LLM_ARCH_DEEPSEEK2:
{
const bool is_lite = (hparams.n_layer == 27);
// lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B
const bool is_lite = (hparams.n_layer == 27 || hparams.n_layer == 26);
const bool is_mla = (hparams.n_embd_head_k_mla != 0 && hparams.n_embd_head_v_mla != 0);
@ -6874,7 +6890,7 @@ void llama_model::print_info() const {
LLAMA_LOG_INFO("%s: n_ff_shexp = %d\n", __func__, hparams.n_ff_shexp);
}
if (arch == LLM_ARCH_QWEN3MOE || arch == LLM_ARCH_OPENAI_MOE || arch == LLM_ARCH_QWEN3VLMOE) {
if (arch == LLM_ARCH_QWEN3MOE || arch == LLM_ARCH_OPENAI_MOE || arch == LLM_ARCH_QWEN3VLMOE || arch == LLM_ARCH_RND1) {
LLAMA_LOG_INFO("%s: n_ff_exp = %d\n", __func__, hparams.n_ff_exp);
}
@ -7039,6 +7055,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
case LLM_ARCH_DREAM:
case LLM_ARCH_LLADA:
case LLM_ARCH_LLADA_MOE:
case LLM_ARCH_RND1:
{
res = nullptr;
} break;
@ -7232,6 +7249,11 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
llm = std::make_unique<llm_build_llada_moe>(*this, params);
}
break;
case LLM_ARCH_RND1:
{
llm = std::make_unique<llm_build_rnd1>(*this, params);
}
break;
case LLM_ARCH_QWEN2VL:
{
llm = std::make_unique<llm_build_qwen2vl>(*this, params);
@ -7752,6 +7774,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
case LLM_ARCH_QWEN3:
case LLM_ARCH_QWEN3MOE:
case LLM_ARCH_LLADA_MOE:
case LLM_ARCH_RND1:
case LLM_ARCH_OLMO2:
case LLM_ARCH_OLMOE:
case LLM_ARCH_PHI2:
@ -7824,6 +7847,24 @@ int32_t llama_model_meta_count(const llama_model * model) {
return (int)model->gguf_kv.size();
}
const char * llama_model_meta_key_str(llama_model_meta_key key) {
switch (key) {
case LLAMA_MODEL_META_KEY_SAMPLING_SEQUENCE: return "general.sampling.sequence";
case LLAMA_MODEL_META_KEY_SAMPLING_TOP_K: return "general.sampling.top_k";
case LLAMA_MODEL_META_KEY_SAMPLING_TOP_P: return "general.sampling.top_p";
case LLAMA_MODEL_META_KEY_SAMPLING_MIN_P: return "general.sampling.min_p";
case LLAMA_MODEL_META_KEY_SAMPLING_XTC_PROBABILITY: return "general.sampling.xtc_probability";
case LLAMA_MODEL_META_KEY_SAMPLING_XTC_THRESHOLD: return "general.sampling.xtc_threshold";
case LLAMA_MODEL_META_KEY_SAMPLING_TEMP: return "general.sampling.temp";
case LLAMA_MODEL_META_KEY_SAMPLING_PENALTY_LAST_N: return "general.sampling.penalty_last_n";
case LLAMA_MODEL_META_KEY_SAMPLING_PENALTY_REPEAT: return "general.sampling.penalty_repeat";
case LLAMA_MODEL_META_KEY_SAMPLING_MIROSTAT: return "general.sampling.mirostat";
case LLAMA_MODEL_META_KEY_SAMPLING_MIROSTAT_TAU: return "general.sampling.mirostat_tau";
case LLAMA_MODEL_META_KEY_SAMPLING_MIROSTAT_ETA: return "general.sampling.mirostat_eta";
default: return nullptr;
}
}
int32_t llama_model_meta_key_by_index(const llama_model * model, int i, char * buf, size_t buf_size) {
if (i < 0 || i >= (int)model->gguf_kv.size()) {
if (buf_size > 0) {