mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

models : Added support for RND1 Diffusion Language Model (#17433)

Browse Source 
* Converted RND1 model to GGUF weights

* RND1 llama.cpp support v1

* RND1 llama.cpp support v2 non causal bug

* RND1 llama.cpp support v3 doccumentation

* RND1 llama.cpp support v4 clean code

* linting issues

* RND1 pr fixes v1

* RND1 pr fixes v2

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Diffusion documentation edits

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
william pan
2025-11-23 22:16:56 -08:00
committed by GitHub
parent 923ae3c619
commit 4902eebe33
9 changed files with 257 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/CMakeLists.txt
+1
View File
@@ -115,6 +115,7 @@ add_library(llama
models/qwen3vl-moe.cpp
models/qwen3moe.cpp
models/refact.cpp
models/rnd1.cpp
models/rwkv6-base.cpp
models/rwkv6.cpp
models/rwkv6qwen2.cpp
src/llama-arch.cpp
+22
View File
@@ -108,6 +108,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_APERTUS, "apertus" },
{ LLM_ARCH_MINIMAX_M2, "minimax-m2" },
{ LLM_ARCH_COGVLM, "cogvlm" },
{ LLM_ARCH_RND1, "rnd1" },
{ LLM_ARCH_PANGU_EMBED, "pangu-embedded" },
{ LLM_ARCH_UNKNOWN, "(unknown)" },
};
@@ -2446,6 +2447,26 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_VISEXP_FFN_UP, "blk.%d.vis_up" },
},
},
{
LLM_ARCH_RND1,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
{ LLM_TENSOR_OUTPUT, "output" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
{ LLM_TENSOR_ATTN_Q_NORM, "blk.%d.attn_q_norm" },
{ LLM_TENSOR_ATTN_K, "blk.%d.attn_k" },
{ LLM_TENSOR_ATTN_K_NORM, "blk.%d.attn_k_norm" },
{ LLM_TENSOR_ATTN_V, "blk.%d.attn_v" },
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
{ LLM_TENSOR_FFN_GATE_INP, "blk.%d.ffn_gate_inp" },
{ LLM_TENSOR_FFN_GATE_EXPS, "blk.%d.ffn_gate_exps" },
{ LLM_TENSOR_FFN_DOWN_EXPS, "blk.%d.ffn_down_exps" },
{ LLM_TENSOR_FFN_UP_EXPS, "blk.%d.ffn_up_exps" },
},
},
{
LLM_ARCH_UNKNOWN,
{
@@ -2722,6 +2743,7 @@ bool llm_arch_is_diffusion(const llm_arch & arch) {
case LLM_ARCH_DREAM:
case LLM_ARCH_LLADA:
case LLM_ARCH_LLADA_MOE:
case LLM_ARCH_RND1:
return true;
default:
return false;
src/llama-arch.h
+1
View File
@@ -112,6 +112,7 @@ enum llm_arch {
LLM_ARCH_APERTUS,
LLM_ARCH_MINIMAX_M2,
LLM_ARCH_COGVLM,
LLM_ARCH_RND1,
LLM_ARCH_PANGU_EMBED,
LLM_ARCH_UNKNOWN,
};
src/llama-model.cpp
+21 -1
View File
@@ -1036,6 +1036,18 @@ 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);
@@ -3402,6 +3414,7 @@ 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);
@@ -6720,7 +6733,7 @@ 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);
}
@@ -6882,6 +6895,7 @@ 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;
@@ -7075,6 +7089,11 @@ 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);
@@ -7595,6 +7614,7 @@ 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:
src/models/models.h
+4
View File
@@ -431,6 +431,10 @@ struct llm_build_refact : public llm_graph_context {
llm_build_refact(const llama_model & model, const llm_graph_params & params);
};
struct llm_build_rnd1 : public llm_graph_context {
llm_build_rnd1(const llama_model & model, const llm_graph_params & params);
};
struct llm_build_rwkv6 : public llm_build_rwkv6_base {
llm_build_rwkv6(const llama_model & model, const llm_graph_params & params);
};
src/models/rnd1.cpp
+126
View File
@@ -0,0 +1,126 @@
#include "models.h"
// RND1 is a Qwen3Moe AR model converted to diffusion model.
llm_build_rnd1::llm_build_rnd1(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
const int64_t n_embd_head = hparams.n_embd_head_v;
GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
GGML_ASSERT(n_embd_head == hparams.n_rot);
ggml_tensor * cur;
ggml_tensor * inpL;
inpL = build_inp_embd(model.tok_embd);
// inp_pos - contains the positions
ggml_tensor * inp_pos = build_inp_pos();
// Non-causal attention for diffusion
auto * inp_attn = build_attn_inp_no_cache();
ggml_tensor * inp_out_ids = build_inp_out_ids();
for (int il = 0; il < n_layer; ++il) {
ggml_tensor * inpSA = inpL;
// norm
cur = build_norm(inpL,
model.layers[il].attn_norm, NULL,
LLM_NORM_RMS, il);
cb(cur, "attn_norm", il);
// self_attention
{
// compute Q and K and RoPE them
ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
cb(Qcur, "Qcur", il);
ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
cb(Kcur, "Kcur", il);
ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
cb(Vcur, "Vcur", il);
Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, NULL, LLM_NORM_RMS, il);
cb(Qcur, "Qcur_normed", il);
Qcur = ggml_rope_ext(
ctx0, Qcur, inp_pos, nullptr,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
ext_factor, attn_factor, beta_fast, beta_slow
);
Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, NULL, LLM_NORM_RMS, il);
cb(Kcur, "Kcur_normed", il);
Kcur = ggml_rope_ext(
ctx0, Kcur, inp_pos, nullptr,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
ext_factor, attn_factor, beta_fast, beta_slow
);
cb(Qcur, "Qcur", il);
cb(Kcur, "Kcur", il);
cb(Vcur, "Vcur", il);
cur = build_attn(inp_attn,
model.layers[il].wo, model.layers[il].bo,
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
}
if (il == n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
}
ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
cb(ffn_inp, "ffn_inp", il);
// MoE branch
cur = build_norm(ffn_inp,
model.layers[il].ffn_norm, NULL,
LLM_NORM_RMS, il);
cb(cur, "ffn_norm", il);
ggml_tensor * moe_out =
build_moe_ffn(cur,
model.layers[il].ffn_gate_inp,
model.layers[il].ffn_up_exps,
model.layers[il].ffn_gate_exps,
model.layers[il].ffn_down_exps,
nullptr,
n_expert, n_expert_used,
LLM_FFN_SILU, true,
false, 0.0,
LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
il);
cb(moe_out, "ffn_moe_out", il);
cur = moe_out;
cur = ggml_add(ctx0, cur, ffn_inp);
cur = build_cvec(cur, il);
cb(cur, "l_out", il);
// input for next layer
inpL = cur;
}
cur = inpL;
cur = build_norm(cur,
model.output_norm, NULL,
LLM_NORM_RMS, -1);
cb(cur, "result_norm", -1);
res->t_embd = cur;
// lm_head
cur = build_lora_mm(model.output, cur);
cb(cur, "result_output", -1);
res->t_logits = cur;
ggml_build_forward_expand(gf, cur);
}