minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

Bump FlashInfer to 0.6.15.post1 (#31927)

Browse Source 
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
This commit is contained in:
Mohammad Miadh Angkad
2026-07-22 14:21:59 -07:00
committed by GitHub
co-authored by Brayden Zhong
parent c20c48b8fd
commit 0c29c8fece
11 changed files with 85 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/test/kits/attention_unittest/attention_methods/dsa_attention.py
+1
View File
@@ -354,6 +354,7 @@ class DSAMockModelRunner(ModelRunner):
triton_attention_split_tile_size=None,
)
self.server_args = self._server_args_override.install()
self.max_running_requests = pool_batch_size
self.req_to_token_pool = ReqToTokenPool(
size=pool_batch_size,
max_context_len=max_context_len,
python/sglang/test/kits/attention_unittest/attention_methods/mla_attention.py
+1
View File
@@ -282,6 +282,7 @@ class MockMLAModelRunner(ModelRunner):
triton_attention_split_tile_size=None,
)
self.server_args = self._server_args_override.install()
self.max_running_requests = pool_batch_size
self.req_to_token_pool = ReqToTokenPool(
size=pool_batch_size,
max_context_len=max_context_len,