mirrors/vllm
0
0 Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-10-28 09:45:26 +08:00
Code Activity
23,986 Commits 469 Branches 215 Tags
main
Commit Graph
3 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Qingvllm-agentqing.xiao
 		274a5e19a1 [Perf][DSv4.1] Capture the decoder replay graphs on the model graphs' stream (#63155) 
Signed-off-by: Qing <xqoasis@gmail.com>
Signed-off-by: qing.xiao <qing.xiao@bytedance.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
Co-authored-by: qing.xiao <qing.xiao@bytedance.com>
 2026-10-27 13:45:57 -07:00
QingandJiangyun Zhu 5b7742a13f [Bugfix][MRV2] Release the warmup memory cached on the capture streams (#63154) 
Signed-off-by: Qing <xqoasis@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2026-10-27 00:23:16 +00:00
Qingandaoshen02 9bd5c2a058 [Bugfix][DSv4.1] Seed the -1 sentinel in the prefill sparse index workspace (#60613) 
Signed-off-by: Qing <xqoasis@gmail.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
 2026-10-23 07:11:30 +00:00