sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 109 Packages Projects Releases Wiki Activity

model: support GLM MoE DSA arch (NOTE: indexer is not yet supported) (#19460)

Browse Source 
* model: support GLM MoE DSA arch

* working version

* pyright

* keep indexer tensors

* add indexer gguf params

* loaded now

* Apply suggestions from code review

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

* update

* Update src/llama-model.cpp

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

* minor fix and cleanup

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Xuan-Son Nguyen
2026-02-13 14:56:53 +01:00
committed by GitHub
parent cc2aa81513
commit 752584d5f5
10 changed files with 361 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/gguf_writer.py
+9
View File
@@ -771,6 +771,15 @@ class GGUFWriter:
def add_value_length_mla(self, length: int) -> None:
self.add_uint32(Keys.Attention.VALUE_LENGTH_MLA.format(arch=self.arch), length)
def add_indexer_head_count(self, count: int) -> None:
self.add_uint32(Keys.Attention.Indexer.HEAD_COUNT.format(arch=self.arch), count)
def add_indexer_key_length(self, length: int) -> None:
self.add_uint32(Keys.Attention.Indexer.KEY_LENGTH.format(arch=self.arch), length)
def add_indexer_top_k(self, top_k: int) -> None:
self.add_uint32(Keys.Attention.Indexer.TOP_K.format(arch=self.arch), top_k)
def add_max_alibi_bias(self, bias: float) -> None:
self.add_float32(Keys.Attention.MAX_ALIBI_BIAS.format(arch=self.arch), bias)