Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model: add dots3-note (#27060)

Browse Source 
* text: conversion

* init impl

* address review comments

* fix rope

* move to a new llama_kv_cache_dsa_iswa
This commit is contained in:
Xuan-Son Nguyen
2026-08-21 19:52:34 +02:00
committed by GitHub
parent 873e5d8e39
commit 5a32f7b66e
20 changed files with 1412 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/gguf_writer.py
+9
View File
@@ -785,6 +785,15 @@ class GGUFWriter:
def add_key_length_swa(self, length: int) -> None:
self.add_uint32(Keys.Attention.KEY_LENGTH_SWA.format(arch=self.arch), length)
def add_key_length_mla_swa(self, length: int) -> None:
self.add_uint32(Keys.Attention.KEY_LENGTH_MLA_SWA.format(arch=self.arch), length)
def add_value_length_mla_swa(self, length: int) -> None:
self.add_uint32(Keys.Attention.VALUE_LENGTH_MLA_SWA.format(arch=self.arch), length)
def add_kv_lora_rank_swa(self, length: int) -> None:
self.add_uint32(Keys.Attention.KV_LORA_RANK_SWA.format(arch=self.arch), length)
def add_value_length_swa(self, length: int) -> None:
self.add_uint32(Keys.Attention.VALUE_LENGTH_SWA.format(arch=self.arch), length)