minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[DLLM] vectorized joint/low-confidence decoding and skip redundant attn init (#21094)

Browse Source 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
wenxuewuhd
2026-07-30 09:13:14 +03:00
committed by GitHub
co-authored by ronnie_zheng
parent 07a087bf45
commit 36afd442c7
3 changed files with 207 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/ascend/basic_function/dllm/test_npu_llada2_mini.py
-1
View File
@@ -19,7 +19,6 @@ class TestLLaDA2Mini(GSM8KAscendMixin, CustomTestCase):
other_args = [
"--trust-remote-code",
"--disable-radix-cache",
"--mem-fraction-static",
"0.9",
"--max-running-requests",