dylanyunlon ddfd24da27 fix: sync to real-machine verified version — ALL TESTS PASSED ...

真机验证通过的精确版本:
- CUB_NS_QUALIFIER (不是 cub::)
- thread_local inside_cub reentrant guard
- 去掉 -D_CCCL_COMPILER_GCC=1
- total_mem → total_memory

BI-V100 32GB × Iluvatar, CoreX clang++ 编译 51864 bytes .so
expandable_segments:True 被 strip, CUB allocator 接管, 缓存复用确认

2026-08-13 09:52:15 +00:00

..

include

feat: CCCL CachingDeviceAllocator preload — 完整依赖链 288 files

2026-08-13 09:26:41 +00:00

build_cccl_preload.sh

fix: CUB_NS_QUALIFIER for wrapped namespace + drop _CCCL_COMPILER_GCC

2026-08-13 09:31:45 +00:00

cccl_allocator_preload.cu

fix: sync to real-machine verified version — ALL TESTS PASSED

2026-08-13 09:52:15 +00:00

verify_preload.py

fix: sync to real-machine verified version — ALL TESTS PASSED

2026-08-13 09:52:15 +00:00