| |
| |
| |
| |
| @@ -238,8 +238,15 @@ compile_gpu_sources_parallel() { |
| obj="$build_dir/${base}.o" |
| fi |
| |
| - # Skip if object file is newer than source |
| - if [ -f "$obj" ] && [ "$obj" -nt "$src" ]; then |
| + # opencoti-hook: cuda-build-ccache (bug-858) — HEADER-AWARE freshness. The CUDA kernels |
| + # live in .cuh HEADERS; template-instance .cu stubs never change, so comparing the object |
| + # only to its .cu left STALE objects on header edits → stale DSO. Also require the object |
| + # to be newer than the newest ggml-tree header ($OPENCOTI_CUDA_DEPS_NEWEST, exported by |
| + # cuda.sh). Compilation runs through ccache (see cuda.sh), so a header edit then recompiles |
| + # only the TUs whose expanded includes actually changed. The `-z` guard preserves the old |
| + # .cu-only behaviour for any caller that doesn't export the var. |
| + if [ -f "$obj" ] && [ "$obj" -nt "$src" ] \ |
| + && { [ -z "$OPENCOTI_CUDA_DEPS_NEWEST" ] || [ "$obj" -nt "$OPENCOTI_CUDA_DEPS_NEWEST" ]; }; then |
| echo "[$count/$total] Skipping: $base.cu (up to date)" |
| continue |
| fi |
| @@ -298,8 +305,11 @@ compile_ggml_core() { |
| local name="${base%.*}" |
| local obj="$build_dir/ggml-core-${name}.o" |
| |
| - # Skip if object file is newer than source |
| - if [ -f "$obj" ] && [ "$obj" -nt "$src" ]; then |
| + # opencoti-hook: cuda-build-ccache (bug-858) — HEADER-AWARE freshness (see cuda.sh). Skip |
| + # only when the object is newer than the source AND every ggml-tree header, so a header |
| + # edit correctly forces a recompile. `-z` guard keeps the old behaviour if the var is unset. |
| + if [ -f "$obj" ] && [ "$obj" -nt "$src" ] \ |
| + && { [ -z "$OPENCOTI_CUDA_DEPS_NEWEST" ] || [ "$obj" -nt "$OPENCOTI_CUDA_DEPS_NEWEST" ]; }; then |
| echo " Skipping: $base (up to date)" |
| continue |
| fi |
| |
| |
| |
| |
| @@ -293,10 +293,29 @@ collect_gpu_sources "$GGML_CUDA_DIR" "$EXTRA_SOURCES" "$NO_IQ_QUANTS" "$FA_ALL_Q |
| echo " Sources: $NUM_SOURCES .cu files" |
| echo "" |
| |
| +# opencoti-hook: cuda-build-ccache (bug-858) — see docs/protocols/LLAMAFILE_UPGRADE.md. |
| +# The CUDA kernels live in .cuh HEADERS (fattn-vec.cuh, fattn-mma-f16.cuh, ...); the |
| +# template-instance .cu stubs that #include them essentially never change. The per-TU |
| +# incremental skip in build-functions.sh compared each object ONLY to its .cu file, so editing a |
| +# .cuh recompiled NOTHING → a silently STALE DSO (bug-858; same class as the host bug-167 -MMD |
| +# fix, which was never applied to this hand-rolled CUDA loop). Fix: (1) route every TU compile |
| +# through ccache, whose include-manifest invalidates the cached object when the .cu OR any |
| +# included header changes; (2) export the newest header mtime in the ggml tree so the no-ccache |
| +# fallback skip is header-aware. Linking (link_shared_library) stays on raw $NVCC — ccache caches |
| +# compiles only. |
| +CUDA_CC="$NVCC" |
| +if command -v ccache >/dev/null 2>&1; then |
| + CUDA_CC="ccache $NVCC" |
| + echo " ccache: ON for CUDA compilation (header-aware via include manifest)" |
| +else |
| + echo " ccache: NOT FOUND — install ccache for fast + correct incremental CUDA rebuilds" |
| +fi |
| +export OPENCOTI_CUDA_DEPS_NEWEST=$(find "$GGML_CUDA_DIR/../.." \( -name '*.cuh' -o -name '*.h' -o -name '*.hpp' \) -printf '%T@ %p\n' 2>/dev/null | sort -rn | head -1 | cut -d' ' -f2-) |
| + |
| START_TIME=$(date +%s) |
| |
| # Compile GPU sources |
| -compile_gpu_sources_parallel "$NVCC" "$ARCH_FLAGS" "$COMMON_FLAGS" "$BUILD_DIR" "$JOBS_EFF" |
| +compile_gpu_sources_parallel "$CUDA_CC" "$ARCH_FLAGS" "$COMMON_FLAGS" "$BUILD_DIR" "$JOBS_EFF" |
| |
| COMPILE_TIME=$(date +%s) |
| echo "Compilation took $((COMPILE_TIME - START_TIME)) seconds" |
|
|
