sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 108 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
gguf-py/gguf/constants.py
+19
View File
@@ -427,6 +427,7 @@ class MODEL_ARCH(IntEnum):
APERTUS = auto()
COGVLM = auto()
MINIMAXM2 = auto()
RND1 = auto()
PANGU_EMBED = auto()
@@ -797,6 +798,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.APERTUS: "apertus",
MODEL_ARCH.MINIMAXM2: "minimax-m2",
MODEL_ARCH.COGVLM: "cogvlm",
MODEL_ARCH.RND1: "rnd1",
MODEL_ARCH.PANGU_EMBED: "pangu-embedded",
}
@@ -2991,6 +2993,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.VISEXP_UP,
MODEL_TENSOR.VISEXP_DOWN,
],
MODEL_ARCH.RND1: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE_INP,
MODEL_TENSOR.FFN_GATE_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.FFN_UP_EXP,
],
MODEL_ARCH.PANGU_EMBED: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,