sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 167 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/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;