Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into concedo_experimental

Browse Source 
# Conflicts:
#	Makefile
#	tests/test-grad0.c
This commit is contained in:
Concedo
2023-07-25 18:52:48 +08:00
parent 66e4b5141e d5512b782b
commit 3e68cdd26a
13 changed files with 867 additions and 502 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/baby-llama/baby-llama.cpp
+11 -9
View File
@@ -8,6 +8,8 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
static const float rms_norm_eps = 1e-6f;
float frand() {
return (float)rand()/(float)RAND_MAX;
}
@@ -562,7 +564,7 @@ struct ggml_tensor * forward(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
// cur = attention_norm*cur
cur = ggml_mul(ctx0,
@@ -685,7 +687,7 @@ struct ggml_tensor * forward(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
// cur = ffn_norm*cur
// cur shape [n_embd,N,1,1]
@@ -729,7 +731,7 @@ struct ggml_tensor * forward(
{
// inpL shape [n_embd,N,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
// inpL = norm*inpL
// inpL shape [n_embd,N,1,1]
@@ -817,7 +819,7 @@ struct ggml_tensor * forward_batch(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = attention_norm*cur
@@ -981,7 +983,7 @@ struct ggml_tensor * forward_batch(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = ffn_norm*cur
@@ -1034,7 +1036,7 @@ struct ggml_tensor * forward_batch(
{
// inpL shape [n_embd,N*n_batch,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(inpL, n_embd, N*n_batch);
// inpL = norm*inpL
@@ -1104,7 +1106,7 @@ struct ggml_tensor * forward_lora(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
// cur = attention_norm*cur
cur = ggml_mul(ctx0,
@@ -1251,7 +1253,7 @@ struct ggml_tensor * forward_lora(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
// cur = ffn_norm*cur
// cur shape [n_embd,N,1,1]
@@ -1295,7 +1297,7 @@ struct ggml_tensor * forward_lora(
{
// inpL shape [n_embd,N,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
// inpL = norm*inpL
// inpL shape [n_embd,N,1,1]
examples/common.cpp
+8
View File
@@ -177,6 +177,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
break;
}
params.n_gqa = std::stoi(argv[i]);
} else if (arg == "-eps" || arg == "--rms-norm-eps") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.rms_norm_eps = std::stof(argv[i]);
} else if (arg == "--rope-freq-base") {
if (++i >= argc) {
invalid_param = true;
@@ -519,6 +525,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stdout, " -eps N, --rms-norm-eps N rms norm eps (TEMP!!! use 1e-5 for LLaMAv2) (default: %.1e)\n", params.rms_norm_eps);
fprintf(stdout, " --top-k N top-k sampling (default: %d, 0 = disabled)\n", params.top_k);
fprintf(stdout, " --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p);
fprintf(stdout, " --tfs N tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)params.tfs_z);
@@ -615,6 +622,7 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
lparams.n_ctx = params.n_ctx;
lparams.n_batch = params.n_batch;
lparams.n_gqa = params.n_gqa;
lparams.rms_norm_eps = params.rms_norm_eps;
lparams.n_gpu_layers = params.n_gpu_layers;
lparams.main_gpu = params.main_gpu;
lparams.tensor_split = params.tensor_split;
examples/common.h
+12 -11
View File
@@ -22,18 +22,19 @@
int32_t get_num_physical_cores();
struct gpt_params {
uint32_t seed = -1; // RNG seed
uint32_t seed = -1; // RNG seed
int32_t n_threads = get_num_physical_cores();
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_gqa = 1; // grouped-query attention factor (TODO: move to hparams)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited)
int32_t n_gpu_layers = 0; // number of layers to store in VRAM
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_gqa = 1; // grouped-query attention factor (TODO: move to hparams)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited)
int32_t n_gpu_layers = 0; // number of layers to store in VRAM
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
float rms_norm_eps = 1e-6; // rms norm epsilon
float rope_freq_base = 10000.0f; // RoPE base frequency
float rope_freq_scale = 1.0f; // RoPE frequency scaling factor
examples/server/index.html.hpp
+672 -418
View File
File diff suppressed because it is too large Load Diff
examples/server/public/index.html
+98 -29
View File
@@ -73,6 +73,37 @@
margin: 0;
}
fieldset.two {
display: grid;
grid-template: "a a";
gap: 1em;
}
fieldset.three {
display: grid;
grid-template: "a a a";
gap: 1em;
}
details {
border: 1px solid #aaa;
border-radius: 4px;
padding: 0.5em 0.5em 0;
margin-top: 0.5em;
}
summary {
font-weight: bold;
margin: -0.5em -0.5em 0;
padding: 0.5em;
cursor: pointer;
}
details[open] {
padding: 0.5em;
}
textarea {
padding: 5px;
flex-grow: 1;
@@ -125,10 +156,17 @@
const params = signal({
n_predict: 400,
temperature: 0.7,
repeat_last_n: 256,
repeat_penalty: 1.18,
top_k: 40,
top_p: 0.5,
repeat_last_n: 256, // 0 = disable penalty, -1 = context size
repeat_penalty: 1.18, // 1.0 = disabled
top_k: 40, // <= 0 to use vocab size
top_p: 0.5, // 1.0 = disabled
tfs_z: 1.0, // 1.0 = disabled
typical_p: 1.0, // 1.0 = disabled
presence_penalty: 0.0, // 0.0 = disabled
frequency_penalty: 0.0, // 0.0 = disabled
mirostat: 0, // 0/1/2
mirostat_tau: 5, // target entropy
mirostat_eta: 0.1, // learning rate
})
const llamaStats = signal(null)
@@ -264,6 +302,27 @@
const updateSession = (el) => session.value = { ...session.value, [el.target.name]: el.target.value }
const updateParams = (el) => params.value = { ...params.value, [el.target.name]: el.target.value }
const updateParamsFloat = (el) => params.value = { ...params.value, [el.target.name]: parseFloat(el.target.value) }
const updateParamsInt = (el) => params.value = { ...params.value, [el.target.name]: Math.floor(parseFloat(el.target.value)) }
const FloatField = ({label, max, min, name, step, value}) => {
return html`
<div>
<label for="${name}">${label}</label>
<input type="range" id="${name}" min="${min}" max="${max}" step="${step}" name="${name}" value="${value}" oninput=${updateParamsFloat} />
<span>${value}</span>
</div>
`
};
const IntField = ({label, max, min, name, value}) => {
return html`
<div>
<label for="${name}">${label}</label>
<input type="range" id="${name}" min="${min}" max="${max}" name="${name}" value="${value}" oninput=${updateParamsInt} />
<span>${value}</span>
</div>
`
};
return html`
<form>
@@ -272,7 +331,9 @@
<label for="prompt">Prompt</label>
<textarea type="text" name="prompt" value="${session.value.prompt}" rows=4 oninput=${updateSession}/>
</div>
</fieldset>
<fieldset class="two">
<div>
<label for="user">User name</label>
<input type="text" name="user" value="${session.value.user}" oninput=${updateSession} />
@@ -282,7 +343,9 @@
<label for="bot">Bot name</label>
<input type="text" name="char" value="${session.value.char}" oninput=${updateSession} />
</div>
</fieldset>
<fieldset>
<div>
<label for="template">Prompt template</label>
<textarea id="template" name="template" value="${session.value.template}" rows=4 oninput=${updateSession}/>
@@ -292,38 +355,44 @@
<label for="template">Chat history template</label>
<textarea id="template" name="historyTemplate" value="${session.value.historyTemplate}" rows=1 oninput=${updateSession}/>
</div>
<div>
<label for="temperature">Temperature</label>
<input type="range" id="temperature" min="0.0" max="1.0" step="0.01" name="temperature" value="${params.value.temperature}" oninput=${updateParamsFloat} />
<span>${params.value.temperature}</span>
</div>
<div>
<label for="nPredict">Predictions</label>
<input type="range" id="nPredict" min="1" max="2048" step="1" name="n_predict" value="${params.value.n_predict}" oninput=${updateParamsFloat} />
<span>${params.value.n_predict}</span>
</div>
<div>
<label for="repeat_penalty">Penalize repeat sequence</label>
<input type="range" id="repeat_penalty" min="0.0" max="2.0" step="0.01" name="repeat_penalty" value="${params.value.repeat_penalty}" oninput=${updateParamsFloat} />
<span>${params.value.repeat_penalty}</span>
</div>
<div>
<label for="repeat_last_n">Consider N tokens for penalize</label>
<input type="range" id="repeat_last_n" min="0.0" max="2048" name="repeat_last_n" value="${params.value.repeat_last_n}" oninput=${updateParamsFloat} />
<span>${params.value.repeat_last_n}</span>
</div>
</fieldset>
<fieldset class="two">
${IntField({label: "Predictions", max: 2048, min: -1, name: "n_predict", value: params.value.n_predict})}
${FloatField({label: "Temperature", max: 1.5, min: 0.0, name: "temperature", step: 0.01, value: params.value.temperature})}
${FloatField({label: "Penalize repeat sequence", max: 2.0, min: 0.0, name: "repeat_penalty", step: 0.01, value: params.value.repeat_penalty})}
${IntField({label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n})}
${IntField({label: "Top-K sampling", max: 100, min: -1, name: "top_k", value: params.value.top_k})}
${FloatField({label: "Top-P sampling", max: 1.0, min: 0.0, name: "top_p", step: 0.01, value: params.value.top_p})}
</fieldset>
<details>
<summary>More options</summary>
<fieldset class="two">
${FloatField({label: "TFS-Z", max: 1.0, min: 0.0, name: "tfs_z", step: 0.01, value: params.value.tfs_z})}
${FloatField({label: "Typical P", max: 1.0, min: 0.0, name: "typical_p", step: 0.01, value: params.value.typical_p})}
${FloatField({label: "Presence penalty", max: 1.0, min: 0.0, name: "presence_penalty", step: 0.01, value: params.value.presence_penalty})}
${FloatField({label: "Frequency penalty", max: 1.0, min: 0.0, name: "frequency_penalty", step: 0.01, value: params.value.frequency_penalty})}
</fieldset>
<hr />
<fieldset class="three">
<div>
<label><input type="radio" name="mirostat" value="0" checked=${params.value.mirostat == 0} oninput=${updateParamsInt} /> no Mirostat</label>
<label><input type="radio" name="mirostat" value="1" checked=${params.value.mirostat == 1} oninput=${updateParamsInt} /> Mirostat v1</label>
<label><input type="radio" name="mirostat" value="2" checked=${params.value.mirostat == 2} oninput=${updateParamsInt} /> Mirostat v2</label>
</div>
${FloatField({label: "Mirostat tau", max: 10.0, min: 0.0, name: "mirostat_tau", step: 0.01, value: params.value.mirostat_tau})}
${FloatField({label: "Mirostat eta", max: 1.0, min: 0.0, name: "mirostat_eta", step: 0.01, value: params.value.mirostat_eta})}
</fieldset>
</details>
</form>
`
}
// poor mans markdown replacement
const Markdownish = (params) => {
const md = params.text
.replace(/&/g, '&amp;')
.replace(/</g, '&lt;')
.replace(/>/g, '&gt;')
.replace(/^#{1,6} (.*)$/gim, '<h3>$1</h3>')
.replace(/\*\*(.*?)\*\*/g, '<strong>$1</strong>')
.replace(/__(.*?)__/g, '<strong>$1</strong>')
examples/server/server.cpp
+9
View File
@@ -609,6 +609,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
fprintf(stdout, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads);
fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stdout, " -eps N, --rms-norm-eps N rms norm eps (TEMP!!! use 1e-5 for LLaMAv2) (default: %.1e)\n", params.rms_norm_eps);
fprintf(stdout, " --rope-freq-base N RoPE base frequency (default: %.1f)\n", params.rope_freq_base);
fprintf(stdout, " --rope-freq-scale N RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale);
fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
@@ -734,6 +735,14 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
}
params.n_gqa = std::stoi(argv[i]);
}
else if (arg == "-eps" || arg == "--rms-norm-eps") {
if (++i >= argc)
{
invalid_param = true;
break;
}
params.rms_norm_eps = std::stof(argv[i]);
}
else if (arg == "--rope-freq-base")
{
if (++i >= argc)
examples/train-text-from-scratch/train-text-from-scratch.cpp
+17 -15
View File
@@ -16,6 +16,8 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
static const float rms_norm_eps = 1e-6f;
struct random_normal_distribution {
std::mt19937 gen;
std::normal_distribution<float> rd;
@@ -439,7 +441,7 @@ struct ggml_tensor * forward(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
// cur = attention_norm*cur
cur = ggml_mul(ctx0,
@@ -562,7 +564,7 @@ struct ggml_tensor * forward(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
// cur = ffn_norm*cur
// cur shape [n_embd,N,1,1]
@@ -606,7 +608,7 @@ struct ggml_tensor * forward(
{
// inpL shape [n_embd,N,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
// inpL = norm*inpL
// inpL shape [n_embd,N,1,1]
@@ -694,7 +696,7 @@ struct ggml_tensor * forward_batch(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = attention_norm*cur
@@ -857,7 +859,7 @@ struct ggml_tensor * forward_batch(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = ffn_norm*cur
@@ -910,7 +912,7 @@ struct ggml_tensor * forward_batch(
{
// inpL shape [n_embd,N*n_batch,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(inpL, n_embd, N*n_batch);
// inpL = norm*inpL
@@ -979,7 +981,7 @@ struct ggml_tensor * forward_batch_wo_cache(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = attention_norm*cur
@@ -1085,7 +1087,7 @@ struct ggml_tensor * forward_batch_wo_cache(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = ffn_norm*cur
@@ -1138,7 +1140,7 @@ struct ggml_tensor * forward_batch_wo_cache(
{
// inpL shape [n_embd,N*n_batch,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(inpL, n_embd, N*n_batch);
// inpL = norm*inpL
@@ -1203,7 +1205,7 @@ struct ggml_tensor * forward_batch_wo_cache_flash_attn(
// norm
{
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = attention_norm*cur
@@ -1267,7 +1269,7 @@ struct ggml_tensor * forward_batch_wo_cache_flash_attn(
{
// norm
{
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = ffn_norm*cur
@@ -1311,7 +1313,7 @@ struct ggml_tensor * forward_batch_wo_cache_flash_attn(
// norm
{
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(inpL, n_embd, N*n_batch);
// inpL = norm*inpL
@@ -1603,7 +1605,7 @@ struct ggml_tensor * forward_batch_wo_cache_flash_attn_train(
struct my_llama_layer & layer = model->layers[il];
// tensors with values necessary for backward pass are in persistent buf(-1)
// other tensors with buf(0) and buf(1) are only temporary needed, and their memory reused after layer is completed.
use_buf(-1); struct ggml_tensor * t02 = expand(gf, ggml_rms_norm (ctx0, cur)); assert_shape_2d(t02, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t02 = expand(gf, ggml_rms_norm (ctx0, cur, rms_norm_eps)); assert_shape_2d(t02, n_embd, N*n_batch);
use_buf( 0); struct ggml_tensor * t03 = expand(gf, ggml_repeat (ctx0, layer.attention_norm, t02)); assert_shape_2d(t03, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t04 = expand(gf, ggml_mul (ctx0, t02, t03)); assert_shape_2d(t04, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t05 = expand(gf, ggml_mul_mat (ctx0, layer.wq, t04)); assert_shape_2d(t05, n_embd, N*n_batch);
@@ -1623,7 +1625,7 @@ struct ggml_tensor * forward_batch_wo_cache_flash_attn_train(
use_buf(-1); struct ggml_tensor * t19 = expand(gf, ggml_reshape_2d (ctx0, t18, n_embd, N*n_batch)); assert_shape_2d(t19, n_embd, N*n_batch);
use_buf( 0); struct ggml_tensor * t20 = expand(gf, ggml_mul_mat (ctx0, layer.wo, t19)); assert_shape_2d(t20, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t21 = expand(gf, ggml_add (ctx0, t20, cur)); assert_shape_2d(t21, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t22 = expand(gf, ggml_rms_norm (ctx0, t21)); assert_shape_2d(t22, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t22 = expand(gf, ggml_rms_norm (ctx0, t21, rms_norm_eps)); assert_shape_2d(t22, n_embd, N*n_batch);
use_buf( 0); struct ggml_tensor * t23 = expand(gf, ggml_repeat (ctx0, layer.ffn_norm, t22)); assert_shape_2d(t23, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t24 = expand(gf, ggml_mul (ctx0, t23, t22)); assert_shape_2d(t24, n_embd, N*n_batch);
use_buf(-1); struct ggml_tensor * t25 = expand(gf, ggml_mul_mat (ctx0, layer.w3, t24)); assert_shape_2d(t25, n_ff, N*n_batch);
@@ -1666,7 +1668,7 @@ struct ggml_tensor * forward_batch_wo_cache_flash_attn_train(
}
clr_buf(0);
use_buf(0);
struct ggml_tensor * t31 = expand(gf, ggml_rms_norm (ctx0, cur)); assert_shape_2d(t31, n_embd, N*n_batch);
struct ggml_tensor * t31 = expand(gf, ggml_rms_norm (ctx0, cur, rms_norm_eps)); assert_shape_2d(t31, n_embd, N*n_batch);
struct ggml_tensor * t32 = expand(gf, ggml_repeat (ctx0, model->norm, t31)); assert_shape_2d(t32, n_embd, N*n_batch);
struct ggml_tensor * t33 = expand(gf, ggml_mul (ctx0, t32, t31)); assert_shape_2d(t33, n_embd, N*n_batch);
use_buf(-1);