Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-08 22:09:10 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4dca015b7e019d5bfa9d3872b19ad4cf97859c22' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/copilot-instructions.md
#	README.md
#	docs/ops.md
#	docs/ops/CPU.csv
#	docs/ops/CUDA.csv
#	docs/ops/Vulkan.csv
#	ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
LostRuins Concedo
2025-11-16 18:33:58 +08:00
parent 85060da3ce 4dca015b7e
commit 3fe0e39b62
69 changed files with 2798 additions and 856 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+104 -1
View File
@@ -27,6 +27,7 @@
#include <stdexcept>
#include <iostream>
#include "models/afmoe.cpp"
#include "models/apertus.cpp"
#include "models/arcee.cpp"
#include "models/arctic.cpp"
@@ -91,6 +92,7 @@
#include "models/openai-moe-iswa.cpp"
#include "models/openelm.cpp"
#include "models/orion.cpp"
#include "models/pangu-embedded.cpp"
#include "models/phi2.cpp"
#include "models/phi3.cpp"
#include "models/plamo.cpp"
@@ -121,7 +123,6 @@
#include "models/wavtokenizer-dec.cpp"
#include "models/xverse.cpp"
#include "models/graph-context-mamba.cpp"
#include "models/pangu-embedded.cpp"
#if defined(GGML_USE_CLBLAST)
# include "ggml_v3b-opencl.h"
@@ -185,6 +186,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_15B: return "15B";
case LLM_TYPE_16B: return "16B";
case LLM_TYPE_20B: return "20B";
case LLM_TYPE_26B: return "26B";
case LLM_TYPE_27B: return "27B";
case LLM_TYPE_30B: return "30B";
case LLM_TYPE_32B: return "32B";
@@ -796,6 +798,37 @@ void llama_model::load_hparams(llama_model_loader & ml) {
default: type = LLM_TYPE_UNKNOWN;
}
} break;
case LLM_ARCH_AFMOE:
{
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);
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp);
ml.get_key(LLM_KV_EXPERT_SHARED_COUNT, hparams.n_expert_shared);
ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func, false);
ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false);
ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false);
ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false);
// Set up interleaved sliding window attention (ISWA)
// Pattern: 3 sliding - 1 full (global_attn_every_n_layers = 4)
if (hparams.n_swa > 0) {
hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
hparams.set_swa_pattern(4);
} else {
hparams.swa_type = LLAMA_SWA_TYPE_NONE;
}
// Default to sigmoid if not set
if (hparams.expert_gating_func == LLAMA_EXPERT_GATING_FUNC_TYPE_NONE) {
hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID;
}
switch (hparams.n_layer) {
case 56: type = LLM_TYPE_6B; break;
case 32: type = LLM_TYPE_26B; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
case LLM_ARCH_DECI:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
@@ -5903,6 +5936,71 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
}
} break;
case LLM_ARCH_AFMOE:
{
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
// output
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
const int64_t n_ff_exp = hparams.n_ff_exp;
const int64_t n_expert_shared = hparams.n_expert_shared;
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];
// dual attention normalization
layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), {n_embd}, 0);
// attention projections
layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
layer.wk = create_tensor(tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa}, 0);
layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_v_gqa}, 0);
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
// Q/K normalization
layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd_head_k}, 0);
layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd_head_k}, 0);
// attention gating
layer.wqkv_gate = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
// dual ffn normalization
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
layer.ffn_post_norm = create_tensor(tn(LLM_TENSOR_FFN_POST_NORM, "weight", i), {n_embd}, 0);
if (static_cast<uint32_t>(i) >= hparams.n_layer_dense_lead) {
// MoE layers
layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0);
layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, 0);
// grouped expert weights
layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0);
layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, 0);
layer.ffn_up_exps = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0);
// shared expert
if (n_expert_shared > 0) {
const int64_t n_ff_shexp = n_ff_exp * n_expert_shared;
layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_shexp}, 0);
layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {n_ff_shexp, n_embd}, 0);
layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_shexp}, 0);
}
} else {
// Dense layers
layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
}
}
} break;
case LLM_ARCH_ERNIE4_5:
case LLM_ARCH_ERNIE4_5_MOE:
{
@@ -7401,6 +7499,10 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
{
llm = std::make_unique<llm_build_arcee>(*this, params);
} break;
case LLM_ARCH_AFMOE:
{
llm = std::make_unique<llm_build_afmoe>(*this, params);
} break;
case LLM_ARCH_ERNIE4_5:
{
llm = std::make_unique<llm_build_ernie4_5>(*this, params);
@@ -7686,6 +7788,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
case LLM_ARCH_MINIMAX_M2:
case LLM_ARCH_COGVLM:
case LLM_ARCH_PANGU_EMBED:
case LLM_ARCH_AFMOE:
return LLAMA_ROPE_TYPE_NEOX;
case LLM_ARCH_QWEN2VL: