DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-14 12:56:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: support packed INT4 convrot models (#2276)

Browse Source 
Co-authored-by: noctrex <noctrex@gmail.com>
This commit is contained in:
leejetandnoctrex authored and GitHub committed 2026-11-06 00:35:58 +08:00
1 parent 58bb3c1b1c
commit 7952693004
48 files changed
+2003 -102
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/model_io/safetensors_io.cpp
+47 -11
View File
@@ -109,8 +109,9 @@ static ggml_type safetensors_dtype_to_ggml_type(const std::string& dtype) {
struct ComfyQuantConfig {
std::string format;
bool convrot = false;
int group_size = 0;
bool convrot = false;
int group_size = 0;
int weight_group_size = 0;
};
static bool read_comfy_quant_config(std::ifstream& file,
@@ -140,6 +141,12 @@ static bool read_comfy_quant_config(std::ifstream& file,
config.format = json.value("format", "");
config.convrot = json.value("convrot", false);
config.group_size = json.value("convrot_groupsize", 0);
config.weight_group_size = json.value("group_size", 0);
if (config.format == "convrot_w4a4" || config.format == "asym_w4a8_int8") {
// Packed W4 formats imply rotation, including exports without the INT8 convrot flag.
config.convrot = true;
config.group_size = json.value("convrot_groupsize", 256);
}
} catch (const std::exception&) {
set_error(error, "parsing ComfyUI quantization metadata tensor failed: '" + tensor_name + "'");
return false;
@@ -238,8 +245,8 @@ bool read_safetensors_file(const std::string& file_path,
return false;
}
#ifdef SD_USE_UPSTREAM_GGML
if (config.format == "int8_tensorwise") {
set_error(error, "INT8 tensorwise/convrot is not supported by this ggml build (tensor '" + name + "')");
if (config.format == "int8_tensorwise" || config.format == "convrot_w4a4" || config.format == "asym_w4a8_int8") {
set_error(error, "ComfyUI INT8/packed INT4 is not supported by this ggml build (tensor '" + name + "')");
return false;
}
#endif
@@ -340,29 +347,58 @@ bool read_safetensors_file(const std::string& file_path,
if (ends_with(name, ".weight")) {
const std::string module_name = name.substr(0, name.size() - std::string(".weight").size());
auto config = comfy_quant_configs.find(module_name);
if (config != comfy_quant_configs.end() && config->second.format == "int8_tensorwise") {
if (config != comfy_quant_configs.end() &&
(config->second.format == "int8_tensorwise" || config->second.format == "convrot_w4a4" || config->second.format == "asym_w4a8_int8")) {
const int w4_kind = config->second.format == "convrot_w4a4" ? 1 : config->second.format == "asym_w4a8_int8" ? 2
: 0;
if (type != GGML_TYPE_I8) {
set_error(error, "ComfyUI int8_tensorwise weight is not I8: '" + name + "'");
set_error(error, "ComfyUI quantized weight is not I8: '" + name + "'");
return false;
}
if (w4_kind && (tensor_storage.n_dims != 2 || tensor_storage.ne[0] <= 0 ||
tensor_storage.ne[0] > INT64_MAX / 2 || tensor_storage.ne[1] <= 0)) {
set_error(error, "invalid packed INT4 weight shape: '" + name + "'");
return false;
}
const int64_t input_features = tensor_storage.ne[0] * (w4_kind ? 2 : 1);
if (config->second.convrot) {
int group_size_remainder = config->second.group_size;
while (group_size_remainder > 1 && group_size_remainder % 4 == 0) {
group_size_remainder /= 4;
}
if (group_size_remainder != 1 || tensor_storage.ne[0] % config->second.group_size != 0) {
if (group_size_remainder != 1 || config->second.group_size > 256 || input_features % config->second.group_size != 0) {
set_error(error, "invalid ComfyUI convrot group size for tensor '" + name + "'");
return false;
}
}
tensor_storage.is_int8_tensorwise = true;
if (w4_kind) {
auto matches = [&](const std::string& suffix, const std::string& expected_dtype, const std::vector<int64_t>& expected_shape) {
auto entry = header_.find(module_name + suffix);
return entry != header_.end() && entry->value("dtype", "") == expected_dtype &&
(*entry)["shape"] == expected_shape;
};
const int64_t n = tensor_storage.ne[1];
const bool valid = w4_kind == 1
? (matches(".weight_scale", "F32", {n}) || matches(".weight_scale", "F32", {n, 1}))
: config->second.weight_group_size == 16 && input_features % 16 == 0 &&
matches(".weight_codebook", "F32", {16}) &&
(matches(".weight_s_channel", "F32", {n}) || matches(".weight_s_channel", "F32", {n, 1})) &&
matches(".weight_s_rel", "F8_E4M3", {n, input_features / 16});
if (!valid) {
set_error(error, "invalid packed INT4 scales/codebook for tensor '" + name + "'");
return false;
}
}
tensor_storage.is_int8_tensorwise = w4_kind == 0;
tensor_storage.w4_convrot_kind = w4_kind;
tensor_storage.int8_convrot = config->second.convrot;
tensor_storage.int8_convrot_group_size = config->second.group_size;
}
} else if (ends_with(name, ".weight_scale")) {
const std::string module_name = name.substr(0, name.size() - std::string(".weight_scale").size());
} else if (ends_with(name, ".weight_scale") || ends_with(name, ".weight_s_channel")) {
const std::string module_name = name.substr(0, name.rfind('.'));
auto config = comfy_quant_configs.find(module_name);
if (config != comfy_quant_configs.end() && config->second.format == "int8_tensorwise" &&
if (config != comfy_quant_configs.end() &&
(config->second.format == "int8_tensorwise" || config->second.format == "convrot_w4a4" || config->second.format == "asym_w4a8_int8") &&
tensor_storage.n_dims == 2 && tensor_storage.ne[0] == 1) {
tensor_storage.ne[0] = tensor_storage.ne[1];
tensor_storage.ne[1] = 1;