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

[NPU] DeepSeek-V4 adapt sgl-kernel-npu ops (compressor/sparse-attn/sparse-attn-metadata) (#35676)

Browse Source 
Co-authored-by: vstone-w <374330057@qq.com>
Co-authored-by: unclezhou486 <154310456@qq.com>
Co-authored-by: 摆渡人 <2044145178@qq.com>
This commit is contained in:
unclezhou
2026-08-25 15:13:12 +08:00
committed by GitHub
co-authored by vstone-w unclezhou486 摆渡人
parent 61b67316d8
commit e2b50930b9
7 changed files with 91 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/unit/npu/attention/test_npu_ascend_backend.py
+1
View File
@@ -153,6 +153,7 @@ class TestForwardMetadata(unittest.TestCase):
"seq_lens",
"actual_seq_lengths_q",
"actual_seq_lengths_q_pa",
"actual_seq_lengths_q_pa_cpu",
"actual_seq_lengths_kv",
"swa_mask",
"prefix_lens",