ViperEkura 5416c2e8fb perf: replace paged KV cache with contiguous ContiguousCache, decode all groups ... - Add KVCache/CacheView abstract base classes in cache.py - Add ContiguousCache (contiguous per-slot buffer, default) alongside PageCache (paged, renamed from old KVCache) - Merge make_table_tensor + bind into bind_tasks on KVCache interface - Remove task_cached/task_record_hashes from base class (PageCache-only) - Scheduler: decode all position groups instead of just the largest (eliminates 63% group skip rate) - Scheduler: accept optional cache param for swapping implementations - Model layer type hints use CacheView base class - Batch 1-32: 1-7% speedup from eliminating Storage.gather overhead - All 183 inference tests pass		2026-07-05 11:34:36 +08:00
..
api	refactor : 清理工厂和配置系统中的死代码与冗余抽象	2026-06-07 11:39:50 +08:00
core	perf: replace paged KV cache with contiguous ContiguousCache, decode all groups	2026-07-05 11:34:36 +08:00
__init__.py	perf: replace paged KV cache with contiguous ContiguousCache, decode all groups	2026-07-05 11:34:36 +08:00
engine.py	fix : FSDP 优化器顺序、温度除零、调度器静默死亡、ref模型设备	2026-05-29 21:57:44 +08:00
sample.py	fix : 修复策略相关文件的类型注解与抽象方法体	2026-06-14 16:20:10 +08:00