merge: reconcile modelhub with github (keep CUB_NS_QUALIFIER fix)

build: trigger rebuild after merge reconciliation
fix: CUB_NS_QUALIFIER for wrapped namespace + drop _CCCL_COMPILER_GCC
2026-08-13 09:35:35 +00:00 · 2026-08-13 09:34:49 +00:00 · 2026-08-13 09:31:45 +00:00 · 2026-08-13 09:26:41 +00:00 · 2026-08-13 09:26:41 +00:00 · 2026-08-13 09:26:41 +00:00
2 changed files with 5 additions and 4 deletions
--- a/qwen3_6_scripts/cccl_preload/build_cccl_preload.sh
+++ b/qwen3_6_scripts/cccl_preload/build_cccl_preload.sh
@@ -72,8 +72,7 @@ COMMON_FLAGS=(
    # Suppress CCCL warnings that don't affect correctness
    -Wno-unused-function
    -Wno-unknown-pragmas
-    # CUB needs these for non-NVCC compilers
-    -D_CCCL_COMPILER_GCC=1
+    # Non-NVCC: disable arch magic, wrap namespace to avoid ODR conflicts
    -D__CUDA_ARCH_LIST__=700
    -DCUB_DISABLE_NAMESPACE_MAGIC
    -DCUB_WRAPPED_NAMESPACE=cccl_preload
--- a/qwen3_6_scripts/cccl_preload/cccl_allocator_preload.cu
+++ b/qwen3_6_scripts/cccl_preload/cccl_allocator_preload.cu
@@ -41,8 +41,10 @@ static constexpr unsigned int ALLOC_MAX_BIN      = 32;  /* 4 GB */
 static constexpr size_t       ALLOC_MAX_CACHED   = (size_t)8 * 1024 * 1024 * 1024; /* 8GB */

 /* ---- Global allocator singleton ---- */
-static cub::CachingDeviceAllocator& get_allocator() {
-    static cub::CachingDeviceAllocator instance(
+using CubAllocator = CUB_NS_QUALIFIER::CachingDeviceAllocator;
+
+static CubAllocator& get_allocator() {
+    static CubAllocator instance(
        ALLOC_BIN_GROWTH,
        ALLOC_MIN_BIN,
        ALLOC_MAX_BIN,
Author	SHA1	Message	Date
root	19946d4c72	merge: reconcile modelhub with github (keep CUB_NS_QUALIFIER fix)	2026-08-13 09:35:35 +00:00
root	188d3654ef	build: trigger rebuild after merge reconciliation	2026-08-13 09:34:49 +00:00
dylanyunlon	0ac118911d	fix: CUB_NS_QUALIFIER for wrapped namespace + drop _CCCL_COMPILER_GCC CoreX clang++ 不是 GCC，-D_CCCL_COMPILER_GCC=1 和 CCCL 自己的 compiler detection 冲突。 CUB_WRAPPED_NAMESPACE=cccl_preload 使得命名空间变成 cccl_preload::cub，用 CUB_NS_QUALIFIER 宏自动解析正确的命名空间。	2026-08-13 09:31:45 +00:00
dylanyunlon	8d6f9eaeb0	feat: CCCL CachingDeviceAllocator preload — 完整依赖链 288 files 从 cccl_upstream 递归追踪 cub/util_allocator.cuh 的全部 include 依赖: cub/ 9 files (config, util_*, version, detect_cuda_runtime) cuda/ libcudacxx type_traits, concepts, algorithm, iterator... nv/ target macros, preprocessor 总计 288 个头文件 (1.4MB)，打包到 include/ 目录，编译时 -I include 即可完全脱离 CCCL 原始目录结构。 .cu 文件直接 #include <cub/util_allocator.cuh>，走原版 CUB CachingDeviceAllocator，零 mock。 BI-V100 参数: growth=2 bins=[8..32] max_cached=8GB/device	2026-08-13 09:26:41 +00:00
dylanyunlon	967d572073	feat: CCCL CachingDeviceAllocator LD_PRELOAD — bypass CoreX expandable_segments ASSERT 从 CCCL upstream cub/cub/util_allocator.cuh 提取 CachingDeviceAllocator 核心算法，去掉所有 CUB/CCCL 宏依赖，编译为独立 .so。用 LD_PRELOAD 拦截 cudaMalloc/cudaFree，路由到 CUB 的 geometric-bin 缓存分配器。同时在 constructor 中 strip PYTORCH_CUDA_ALLOC_CONF 里的 expandable_segments 配置，避免 CoreX CUDACachingAllocator.cpp:545 ASSERT。 BI-V100 调优参数: bin_growth=8, min_bin=3 (512B), max_bin=13 (~550MB) max_cached_bytes=4GB per device (32GB卡的合理上限) 真机测试步骤: 1. bash build_cccl_preload.sh 2. LD_PRELOAD=./libcccl_allocator.so CCCL_ALLOC_DEBUG=1 \ PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \ python3 verify_preload.py	2026-08-13 09:26:41 +00:00
dylanyunlon	502ea2fc96	fix: remove expandable_segments — CoreX CUDACachingAllocator不支持 BI-V100 CoreX PyTorch的CUDACachingAllocator.cpp:545没有实现 expandable segment特性，导致模型加载阶段(VocabParallelEmbedding) 直接INTERNAL ASSERT FAILED崩溃。替换为max_split_size_mb:512减少内存碎片化。	2026-08-13 09:26:41 +00:00
Claude	327c2c9044	feat(CCCL): LD_PRELOAD CachingDeviceAllocator — intercept cudaMalloc/cudaFree Route C: replace PyTorch's cudaMalloc/cudaFree with CCCL CUB's CachingDeviceAllocator via LD_PRELOAD. Eliminates driver-level allocation overhead by reusing freed GPU memory from a bin-based cache. Based on cccl_upstream/cub/cub/util_allocator.cuh (901 lines). Self-contained .so with no CCCL header dependencies at compile time. Files: - cccl_preload_allocator.cu: the allocator (405 lines) - build_cccl_preload_allocator.sh: build script (corex clang++ or g++ fallback) - test_cccl_preload.sh: smoke test suite for BI-V100 - patch_ops.sh: build during docker build - computility-run.yaml: LD_PRELOAD env var for runtime Config via env: CCCL_ALLOC_BIN_GROWTH=8, MIN_BIN=3, MAX_BIN=13, MAX_CACHED_MB=4096 Test on real machine: cd qwen3_6_scripts && bash test_cccl_preload.sh	2026-08-13 09:21:52 +00:00