5 Commits

Author SHA1 Message Date
STEVENTAN100
5478b117c8 Add gpu_memory_utilization to engine arguments
Prevent shortage of GPU memory.
2025-10-21 10:32:54 +08:00
STEVENTAN100
22d21b9b23 Refactor context budget control return values and correct attribute name error
Refactor context budget control to always return a 4-tuple for consistency. Correct attribute name `ppl_chunking` error.
2025-10-21 10:28:30 +08:00
YerbaPage
56f1b4e35d add data 2025-10-17 15:39:02 +08:00
YerbaPage
2d6c9ee950 fix repoqa 2025-10-16 08:32:22 +08:00
YerbaPage
a391badfe1 packaging 2025-10-11 21:33:12 +08:00