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

dsv4.1: remaining model and runtime integration (#38798)

Browse Source 
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <xiaoyu.zhang@radixark.ai>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
This commit is contained in:
Liangsheng Yin
2026-09-18 02:55:30 -07:00
committed by GitHub
co-authored by BBuf Claude Opus 5 Xiaoyu Zhang Yuwei An Khoa Pham Yuhao Yang Zhichen Zeng Ke Bao
parent 1b200ffaaa
commit a6cf05817f
103 changed files with 8807 additions and 723 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/kernels/ops/attention/test_q8kv8_sparse_prefill_backend.py
+3 -1
View File
@@ -175,7 +175,9 @@ def _make_backend(
dsv4_prefill_backend: str = "auto",
) -> DeepseekV4AttnBackend:
backend = DeepseekV4AttnBackend.__new__(DeepseekV4AttnBackend)
backend.forward_metadata = SimpleNamespace(sparse_prefill_cache=None)
backend.forward_metadata = SimpleNamespace(
sparse_prefill_cache=None, late_layer_tail=None
)
backend.req_to_token = req_to_token
backend.sparse_prefill_workspace = SparsePrefillWorkspace(device)
backend.softmax_scale = 512**-0.5