nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 21 Packages Projects Releases Wiki Activity

models : support qwen3.5 series (#19468)

Browse Source 
* support qwen3.5 series

* remove deepstack for now, and some code clean

* code clean

* add FULL_ATTENTION_INTERVAL metadata

* code clean

* reorder v heads for linear attention to avoid expensive interleaved repeat
This commit is contained in:
JJJYmmm
2026-02-10 18:00:26 +02:00
committed by GitHub
parent 9a96352729
commit fc0fe40049
17 changed files with 2096 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/gguf_writer.py
+3
View File
@@ -708,6 +708,9 @@ class GGUFWriter:
def add_leading_dense_block_count(self, length: int) -> None:
self.add_uint32(Keys.LLM.LEADING_DENSE_BLOCK_COUNT.format(arch=self.arch), length)
def add_full_attention_interval(self, interval: int) -> None:
self.add_uint32(Keys.LLM.FULL_ATTENTION_INTERVAL.format(arch=self.arch), interval)
def add_feed_forward_length(self, length: int | Sequence[int]) -> None:
if isinstance(length, int):
self.add_uint32(Keys.LLM.FEED_FORWARD_LENGTH.format(arch=self.arch), length)