Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4ef9301e4de5ea8f5ebf20b107cf30de0070bf2a' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/labeler.yml
#	docs/multimodal.md
#	embd_res/ggml-vocab-gemma-4.gguf
#	embd_res/ggml-vocab-gemma-4.gguf.inp
#	embd_res/ggml-vocab-gemma-4.gguf.out
#	ggml/src/ggml-sycl/fattn-tile.cpp
#	ggml/src/ggml-sycl/fattn-tile.hpp
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	ggml/src/ggml-sycl/fattn.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q8_0.cpp
#	tests/CMakeLists.txt
#	tests/test-jinja.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-04-11 09:38:50 +08:00
parent f4fbd94129 4ef9301e4d
commit 8b90bfe094
42 changed files with 1055 additions and 541 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-vocab.cpp
+11 -2
View File
@@ -884,8 +884,17 @@ struct llm_tokenizer_bpe_session {
if (token == LLAMA_TOKEN_NULL) {
for (auto j = str.begin(); j != str.end(); ++j) {
std::string byte_str(1, *j);
auto token_multibyte = vocab.text_to_token(byte_str);
llama_token token_multibyte = LLAMA_TOKEN_NULL;
if (tokenizer.byte_encode) {
std::string byte_str(1, *j);
token_multibyte = vocab.text_to_token(byte_str);
} else {
// For non-byte-encoded BPE (e.g. gemma-4), byte tokens use <0xXX> format
static const char * hex = "0123456789ABCDEF";
const uint8_t ch = (uint8_t)*j;
const char buf[7] = { '<', '0', 'x', hex[ch >> 4], hex[ch & 15], '>', 0 };
token_multibyte = vocab.text_to_token(buf);
}
if (token_multibyte != LLAMA_TOKEN_NULL) {
output.push_back(token_multibyte);
}
src/models/gemma3n-iswa.cpp
+7 -5
View File
@@ -250,27 +250,29 @@ ggml_tensor * llm_build_gemma3n_iswa::calc_magnitude(ggml_tensor * x) {
ggml_tensor * llm_build_gemma3n_iswa::build_inp_per_layer() {
auto inp = std::make_unique<llm_graph_input_embd>(n_embd);
ggml_tensor * inp_per_layer;
float tok_embd_scale = sqrtf((float) n_embd_altup);
if (ubatch.token) {
inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, ubatch.n_tokens);
ggml_set_input(inp->tokens);
res->t_inp_tokens = inp->tokens;
inp_per_layer = ggml_get_rows(ctx0, model.per_layer_tok_embd, inp->tokens);
inp_per_layer = ggml_get_rows (ctx0, model.per_layer_tok_embd, inp->tokens);
inp_per_layer = ggml_reshape_3d(ctx0, inp_per_layer, n_embd_altup, n_layer, n_tokens);
inp_per_layer = ggml_scale(ctx0, inp_per_layer, sqrtf((float) n_embd_altup));
inp_per_layer = ggml_scale (ctx0, inp_per_layer, tok_embd_scale);
cb(inp_per_layer, "inp_per_layer_selected", -1);
res->add_input(std::move(inp));
} else {
// Vision embedding path: use padding token (ID=0) embedding
// Multimodal embedding path: use padding token (ID=0) embedding
// TODO: verify if this is the correct behavior in transformers implementation
const int64_t embd_size = model.per_layer_tok_embd->ne[0]; // n_embd_altup * n_layer
// Extract and dequantize padding token embedding (row 0)
ggml_tensor * padding = ggml_view_1d(ctx0, model.per_layer_tok_embd, embd_size, 0);
inp_per_layer = ggml_cast(ctx0, padding, GGML_TYPE_F32);
inp_per_layer = ggml_cast (ctx0, padding, GGML_TYPE_F32);
inp_per_layer = ggml_scale(ctx0, inp_per_layer, tok_embd_scale);
// Reshape to [n_embd_altup, n_layer, 1]
inp_per_layer = ggml_reshape_3d(ctx0, inp_per_layer, n_embd_altup, n_layer, 1);
cb(inp_per_layer, "inp_per_layer_vision", -1);
cb(inp_per_layer, "inp_per_layer_multimodal", -1);
}
return inp_per_layer;
}
src/models/gemma4-iswa.cpp
+6 -4
View File
@@ -265,6 +265,7 @@ ggml_tensor * llm_build_gemma4_iswa::build_inp_per_layer() {
auto inp = std::make_unique<llm_graph_input_embd>(n_embd);
ggml_tensor * inp_per_layer;
float tok_embd_scale = sqrtf((float) n_embd_per_layer);
if (ubatch.token) {
inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, ubatch.n_tokens);
ggml_set_input(inp->tokens);
@@ -272,22 +273,23 @@ ggml_tensor * llm_build_gemma4_iswa::build_inp_per_layer() {
inp_per_layer = ggml_get_rows (ctx0, model.per_layer_tok_embd, inp->tokens);
inp_per_layer = ggml_reshape_3d(ctx0, inp_per_layer, n_embd_per_layer, n_layer, n_tokens);
inp_per_layer = ggml_scale (ctx0, inp_per_layer, sqrtf((float) n_embd_per_layer));
inp_per_layer = ggml_scale (ctx0, inp_per_layer, tok_embd_scale);
cb(inp_per_layer, "inp_per_layer_selected", -1);
res->add_input(std::move(inp));
} else {
// Vision embedding path: use padding token (ID=0) embedding
// Multimodal embedding path: use padding token (ID=0) embedding
// TODO: verify if this is the correct behavior in transformers implementation
const int64_t embd_size = model.per_layer_tok_embd->ne[0]; // n_embd_per_layer * n_layer
// Extract and dequantize padding token embedding (row 0)
ggml_tensor * padding = ggml_view_1d(ctx0, model.per_layer_tok_embd, embd_size, 0);
inp_per_layer = ggml_cast(ctx0, padding, GGML_TYPE_F32);
inp_per_layer = ggml_cast (ctx0, padding, GGML_TYPE_F32);
inp_per_layer = ggml_scale(ctx0, inp_per_layer, tok_embd_scale);
// Reshape to [n_embd_per_layer, n_layer, 1]
inp_per_layer = ggml_reshape_3d(ctx0, inp_per_layer, n_embd_per_layer, n_layer, 1);
cb(inp_per_layer, "inp_per_layer_vision", -1);
cb(inp_per_layer, "inp_per_layer_multimodal", -1);
}
return inp_per_layer;
}