Skip to content

Compile bug: #1

Open
Open
Compile bug:#1
@drscrewdriver

Description

@drscrewdriver
drscrewdriver
opened on Apr 26, 2026

Git commit

[ 56%] Linking CXX shared library ../bin/libllama.so
[ 56%] Built target llama
[ 57%] Building CXX object common/CMakeFiles/common.dir/arg.cpp.o
[ 57%] Building CXX object examples/simple/CMakeFiles/llama-simple.dir/simple.cpp.o
[ 57%] Building C object tests/CMakeFiles/test-c.dir/test-c.c.o
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd.cpp.o
[ 57%] Linking C executable ../bin/test-c
[ 57%] Built target test-c
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd-audio.cpp.o
[ 57%] Linking CXX executable ../../bin/llama-simple
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)30, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)' /usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)8, (ggml_type)30>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)1, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)' /usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)8, (ggml_type)1>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)1, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)' /usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)8, (ggml_type)1>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)1, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)' /usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)8, (ggml_type)1>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)30, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)' /usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)8, (ggml_type)30>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)8, (ggml_type)30>(ggml_backend_cuda_context&, ggml_tensor*)' /usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)30, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
collect2: error: ld returned 1 exit status
gmake[2]: *** [examples/simple/CMakeFiles/llama-simple.dir/build.make:102: bin/llama-simple] Error 1
gmake[1]: *** [CMakeFiles/Makefile2:4055: examples/simple/CMakeFiles/llama-simple.dir/all] Error 2
gmake[1]: *** Waiting for unfinished jobs....
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd-image.cpp.o
[ 57%] Building CXX object common/CMakeFiles/common.dir/chat-auto-parser-generator.cpp.o
[ 57%] Building CXX object common/CMakeFiles/common.dir/chat-auto-parser-helpers.cpp.o
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd-helper.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/clip.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/cogvlm.cpp.o
[ 58%] Building CXX object common/CMakeFiles/common.dir/chat-diff-analyzer.cpp.o
[ 58%] Building CXX object common/CMakeFiles/common.dir/chat-peg-parser.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/conformer.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/dotsocr.cpp.o
[ 59%] Building CXX object common/CMakeFiles/common.dir/chat.cpp.o
[ 59%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/gemma4a.cpp.o
[ 59%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/gemma4v.cpp.o
[ 59%] Building CXX object common/CMakeFiles/common.dir/common.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/glm4v.cpp.o
[ 60%] Building CXX object common/CMakeFiles/common.dir/console.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/hunyuanocr.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/internvl.cpp.o
[ 60%] Building CXX object common/CMakeFiles/common.dir/debug.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/kimivl.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/kimik25.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/nemotron-v2-vl.cpp.o
[ 60%] Building CXX object common/CMakeFiles/common.dir/download.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/llama4.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/llava.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/minicpmv.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/paddleocr.cpp.o
[ 61%] Building CXX object common/CMakeFiles/common.dir/hf-cache.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/pixtral.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/qwen2vl.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/qwen3vl.cpp.o
[ 62%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/qwen3a.cpp.o
[ 62%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/step3vl.cpp.o
[ 62%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/siglip.cpp.o
[ 63%] Building CXX object common/CMakeFiles/common.dir/json-partial.cpp.o
[ 63%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/whisper-enc.cpp.o
[ 63%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/deepseekocr.cpp.o
[ 63%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/mobilenetv5.cpp.o
[ 64%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/youtuvl.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/json-schema-to-grammar.cpp.o
[ 64%] Linking CXX shared library ../../bin/libmtmd.so
[ 64%] Built target mtmd
[ 64%] Building CXX object common/CMakeFiles/common.dir/llguidance.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/log.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/ngram-cache.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/ngram-map.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/ngram-mod.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/peg-parser.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/preset.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/regex-partial.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/reasoning-budget.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/sampling.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/speculative.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/unicode.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/lexer.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/parser.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/runtime.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/value.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/string.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/caps.cpp.o
[ 67%] Building CXX object common/CMakeFiles/common.dir/__/license.cpp.o
[ 67%] Linking CXX static library libcommon.a
[ 67%] Built target common
gmake: *** [Makefile:146: all] Error 2

Operating systems

Linux

GGML backends

CUDA

Problem description & steps to reproduce

build fail

First Bad Commit

No response

Compile command

cmake -B build     -DGGML_CUDA=ON     -DCMAKE_CUDA_ARCHITECTURES=native     -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j4

Relevant log output

root@DESKTOP-N5Q35MQ:/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55# cmake --build build --config Release -j4
[  0%] Building CXX object common/CMakeFiles/build_info.dir/build-info.cpp.o
[  0%] Building C object ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o
[  0%] Building CXX object vendor/cpp-httplib/CMakeFiles/cpp-httplib.dir/httplib.cpp.o
[  0%] Building C object examples/gguf-hash/CMakeFiles/sha256.dir/deps/sha256/sha256.c.o
[  0%] Built target build_info
[  0%] Building CXX object ggml/src/CMakeFiles/ggml-base.dir/ggml.cpp.o
[  0%] Built target sha256
[  0%] Building C object ggml/src/CMakeFiles/ggml-base.dir/ggml-alloc.c.o
[  1%] Building C object examples/gguf-hash/CMakeFiles/xxhash.dir/deps/xxhash/xxhash.c.o
[  1%] Building C object examples/gguf-hash/CMakeFiles/sha1.dir/deps/sha1/sha1.c.o
[  1%] Built target sha1
[  1%] Building CXX object ggml/src/CMakeFiles/ggml-base.dir/ggml-backend.cpp.o
[  1%] Built target xxhash
[  1%] Building CXX object ggml/src/CMakeFiles/ggml-base.dir/ggml-backend-meta.cpp.o
[  2%] Building CXX object tools/mtmd/CMakeFiles/llama-llava-cli.dir/deprecation-warning.cpp.o
[  2%] Building CXX object tools/mtmd/CMakeFiles/llama-gemma3-cli.dir/deprecation-warning.cpp.o
[  2%] Linking CXX executable ../../bin/llama-llava-cli
[  2%] Built target llama-llava-cli
[  3%] Building CXX object ggml/src/CMakeFiles/ggml-base.dir/ggml-opt.cpp.o
[  4%] Linking CXX executable ../../bin/llama-gemma3-cli
[  4%] Built target llama-gemma3-cli
[  4%] Building CXX object ggml/src/CMakeFiles/ggml-base.dir/ggml-threading.cpp.o
[  5%] Building CXX object tools/mtmd/CMakeFiles/llama-minicpmv-cli.dir/deprecation-warning.cpp.o
[  5%] Linking CXX executable ../../bin/llama-minicpmv-cli
[  5%] Built target llama-minicpmv-cli
[  5%] Building C object ggml/src/CMakeFiles/ggml-base.dir/ggml-quants.c.o
[  5%] Building CXX object tools/mtmd/CMakeFiles/llama-qwen2vl-cli.dir/deprecation-warning.cpp.o
[  5%] Linking CXX executable ../../bin/llama-qwen2vl-cli
[  5%] Built target llama-qwen2vl-cli
[  5%] Building C object ggml/src/CMakeFiles/ggml-base.dir/ggml-turbo-quant.c.o
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-turbo-quant.c: In function ‘dequantize_row_turbo3_tcq’:
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-turbo-quant.c:308:71: warning: unused parameter ‘x’ [-Wunused-parameter]        
  308 | void dequantize_row_turbo3_tcq(const block_turbo3_tcq * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k) {
      |                                ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-turbo-quant.c: In function ‘dequantize_row_turbo2_tcq’:
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-turbo-quant.c:349:71: warning: unused parameter ‘x’ [-Wunused-parameter]        
  349 | void dequantize_row_turbo2_tcq(const block_turbo2_tcq * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k) {
      |                                ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-turbo-quant.c: At top level:
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-turbo-quant.c:27:20: warning: ‘CENTROIDS_1BIT’ defined but not used [-Wunused-const-variable=]
   27 | static const float CENTROIDS_1BIT[2] = { -0.070711f, 0.070711f };  /* for d=128 */
      |                    ^~~~~~~~~~~~~~
[  5%] Building CXX object ggml/src/CMakeFiles/ggml-base.dir/gguf.cpp.o
[  5%] Linking CXX shared library ../../bin/libggml-base.so
[  5%] Built target ggml-base
[  6%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/ggml-cpu.cpp.o
[  6%] Building C object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/ggml-cpu.c.o
[  6%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o
[  6%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o
[  6%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/repack.cpp.o
[  6%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/hbm.cpp.o
[  6%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.o
[  6%] Building C object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/quants.c.o
[  6%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argmax.cu.o
[  6%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/traits.cpp.o
[  7%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.o
[  7%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/amx/amx.cpp.o
[  8%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/amx/mmq.cpp.o
[  8%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/binary-ops.cpp.o
[  8%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/unary-ops.cpp.o
[  8%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o
[  8%] Linking CXX static library libcpp-httplib.a
[  8%] Built target cpp-httplib
[  8%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/vec.cpp.o
[  8%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o
[  8%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/ops.cpp.o
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cpu/ops.cpp: In function ‘void ggml_compute_forward_clamp(const ggml_compute_params*, ggml_tensor*)’:
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cpu/ops.cpp:5574:12: warning: enumeration value ‘GGML_TYPE_TURBO3_0’ not handled in switch [-Wswitch]
 5574 |     switch (src0->type) {
      |            ^
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cpu/ops.cpp:5574:12: warning: enumeration value ‘GGML_TYPE_TURBO4_0’ not handled in switch [-Wswitch]
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cpu/ops.cpp:5574:12: warning: enumeration value ‘GGML_TYPE_TURBO2_0’ not handled in switch [-Wswitch]
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cpu/ops.cpp:5574:12: warning: enumeration value ‘GGML_TYPE_TURBO3_TCQ’ not handled in switch [-Wswitch]
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cpu/ops.cpp:5574:12: warning: enumeration value ‘GGML_TYPE_TURBO2_TCQ’ not handled in switch [-Wswitch]
[  8%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/llamafile/sgemm.cpp.o
[  8%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/concat.cu.o
[  9%] Building C object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/x86/quants.c.o
[  9%] Building CXX object ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/x86/repack.cpp.o
[  9%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.o
[  9%] Linking CXX shared library ../../bin/libggml-cpu.so
[  9%] Built target ggml-cpu
[  9%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/convert.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/count-equal.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cpy.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.o
[ 10%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cumsum.cu.o
[ 11%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diag.cu.o
[ 11%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.o
[ 11%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile.cu.o
[ 11%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-wmma-f16.cu.o
[ 11%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn.cu.o
[ 11%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fill.cu.o
[ 12%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gated_delta_net.cu.o
[ 12%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o
[ 12%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ggml-cuda.cu.o
[ 12%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gla.cu.o
[ 12%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/im2col.cu.o
[ 12%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mean.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmid.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvf.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvq.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/norm.cu.o
[ 13%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-adamw.cu.o
[ 14%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o
[ 14%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o
[ 14%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o
[ 14%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad_reflect_1d.cu.o
[ 14%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pool2d.cu.o
[ 14%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/quantize.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/roll.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/rope.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/scale.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o
[ 15%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softmax.cu.o
[ 16%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/solve_tri.cu.o
[ 16%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-conv.cu.o
[ 16%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o
[ 16%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sum.cu.o
[ 16%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o
[ 16%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/top-k.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/topk-moe.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tq3-native.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tri.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tsembd.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/turbo-sink.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/turbo-wht.cu.o
[ 17%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/unary.cu.o
[ 18%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/upscale.cu.o
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cuda/turbo-wht.cu:55:6: warning: no previous declaration for ‘void ggml_cuda_op_turbo_wht(ggml_backend_cuda_context&, ggml_tensor*)’ [-Wmissing-declarations]
   55 | void ggml_cuda_op_turbo_wht(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
      |      ^~~~~~~~~~~~~~~~~~~~~~
[ 18%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/wkv.cu.o
[ 18%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq112-dv112.cu.o
[ 18%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq128-dv128.cu.o
[ 18%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq256-dv256.cu.o
[ 18%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq40-dv40.cu.o
[ 19%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq512-dv512.cu.o
[ 19%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq576-dv512.cu.o
[ 19%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq64-dv64.cu.o
[ 19%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq72-dv72.cu.o
[ 19%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq80-dv80.cu.o
[ 19%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq96-dv96.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_32.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o
[ 20%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o
[ 21%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_32.cu.o
[ 21%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o
[ 21%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o
[ 21%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o
[ 21%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o
[ 21%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o
[ 22%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o
[ 23%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu.o
[ 23%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq1_s.cu.o
[ 23%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_s.cu.o
[ 23%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xs.cu.o
[ 23%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xxs.cu.o
[ 23%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_s.cu.o
[ 24%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_xxs.cu.o
[ 24%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_nl.cu.o
[ 24%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_xs.cu.o
[ 24%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-mxfp4.cu.o
[ 24%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-nvfp4.cu.o
[ 24%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_k.cu.o
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q3_k.cu.o
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_0.cu.o
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cuda/fattn.cu:12:6: warning: no previous declaration for ‘void turbo_innerq_update_fattn_scales(const float*)’ [-Wmissing-declarations]
   12 | void turbo_innerq_update_fattn_scales(const float * scale_inv) {
      |      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cuda/fattn.cu:16:6: warning: no previous declaration for ‘void turbo_innerq_init_fattn()’ [-Wmissing-declarations]
   16 | void turbo_innerq_init_fattn() {
      |      ^~~~~~~~~~~~~~~~~~~~~~~
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cuda/fattn.cu:25:6: warning: no previous declaration for ‘void turbo_q_calibrate_init()’ [-Wmissing-declarations]
   25 | void turbo_q_calibrate_init() {
      |      ^~~~~~~~~~~~~~~~~~~~~~
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/ggml/src/ggml-cuda/fattn.cu:38:6: warning: no previous declaration for ‘void turbo_q_calibrate_finalize()’ [-Wmissing-declarations]
   38 | void turbo_q_calibrate_finalize() {
      |      ^~~~~~~~~~~~~~~~~~~~~~~~~~
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_1.cu.o
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_k.cu.o
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_0.cu.o
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_1.cu.o
[ 25%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_k.cu.o
[ 26%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q6_k.cu.o
[ 26%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q8_0.cu.o
[ 26%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-tq3_0.cu.o
[ 26%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-tq3_1s.cu.o
[ 26%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-tq3_4s.cu.o
[ 26%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_1.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_10.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_11.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_12.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_13.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_14.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_15.cu.o
[ 27%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_16.cu.o
[ 28%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_2.cu.o
[ 28%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_3.cu.o
[ 28%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_4.cu.o
[ 28%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_5.cu.o
[ 28%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_6.cu.o
[ 28%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_7.cu.o
[ 29%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_8.cu.o
[ 29%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_9.cu.o
[ 29%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q4_0-q4_0.cu.o
[ 29%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q8_0-q8_0.cu.o
[ 29%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-bf16-f16.cu.o
[ 29%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-f16-f16.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-bf16-bf16.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q8_0-turbo2_0.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo2_0-q8_0.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo2_0-turbo2_0.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo2_0-turbo3_0.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo3_0-turbo2_0.cu.o
[ 30%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q8_0-turbo3_0.cu.o
[ 31%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo3_0-q8_0.cu.o
[ 31%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo3_0-turbo3_0.cu.o
[ 31%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo3_0-turbo4_0.cu.o
[ 31%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo4_0-turbo3_0.cu.o
[ 31%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q8_0-turbo4_0.cu.o
[ 31%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo4_0-q8_0.cu.o
[ 32%] Building CUDA object ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-turbo4_0-turbo4_0.cu.o
[ 32%] Linking CUDA shared library ../../../bin/libggml-cuda.so
[ 32%] Built target ggml-cuda
[ 32%] Building CXX object ggml/src/CMakeFiles/ggml.dir/ggml-backend-dl.cpp.o
[ 32%] Building CXX object ggml/src/CMakeFiles/ggml.dir/ggml-backend-reg.cpp.o
[ 33%] Linking CXX shared library ../../bin/libggml.so
[ 33%] Built target ggml
[ 33%] Building CXX object examples/gguf/CMakeFiles/llama-gguf.dir/gguf.cpp.o
[ 33%] Building CXX object examples/gguf-hash/CMakeFiles/llama-gguf-hash.dir/gguf-hash.cpp.o
[ 33%] Building CXX object src/CMakeFiles/llama.dir/llama.cpp.o
[ 33%] Building CXX object src/CMakeFiles/llama.dir/llama-adapter.cpp.o
[ 33%] Linking CXX executable ../../bin/llama-gguf
[ 33%] Built target llama-gguf
[ 33%] Building CXX object src/CMakeFiles/llama.dir/llama-arch.cpp.o
[ 34%] Linking CXX executable ../../bin/llama-gguf-hash
[ 34%] Built target llama-gguf-hash
[ 35%] Building CXX object src/CMakeFiles/llama.dir/llama-batch.cpp.o
[ 35%] Building CXX object src/CMakeFiles/llama.dir/llama-chat.cpp.o
[ 35%] Building CXX object src/CMakeFiles/llama.dir/llama-context.cpp.o
[ 35%] Building CXX object src/CMakeFiles/llama.dir/llama-cparams.cpp.o
[ 35%] Building CXX object src/CMakeFiles/llama.dir/llama-grammar.cpp.o
[ 35%] Building CXX object src/CMakeFiles/llama.dir/llama-graph.cpp.o
[ 36%] Building CXX object src/CMakeFiles/llama.dir/llama-hparams.cpp.o
[ 36%] Building CXX object src/CMakeFiles/llama.dir/llama-impl.cpp.o
[ 36%] Building CXX object src/CMakeFiles/llama.dir/llama-io.cpp.o
[ 36%] Building CXX object src/CMakeFiles/llama.dir/llama-kv-cache.cpp.o
[ 36%] Building CXX object src/CMakeFiles/llama.dir/llama-kv-cache-iswa.cpp.o
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/src/llama-kv-cache.cpp: In constructor ‘llama_kv_cache::llama_kv_cache(const llama_model&, ggml_type, ggml_type, bool, bool, bool, uint32_t, uint32_t, uint32_t, uint32_t, llama_swa_type, const llama_memory_i::layer_filter_cb&, const llama_memory_i::layer_reuse_cb&)’:
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/src/llama-kv-cache.cpp:294:18: warning: variable ‘promote_k’ set but not used [-Wunused-but-set-variable]
  294 |             bool promote_k = false;
      |                  ^~~~~~~~~
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/src/llama-kv-cache.cpp:373:23: warning: unused variable ‘k’ [-Wunused-variable]
  373 |         ggml_tensor * k = has_k ? ggml_new_tensor_3d(ctx, layer_type_k, n_embd_k_gqa, kv_size, n_stream) : nullptr;
      |                       ^
/opt/llama.cpp-dgx/llama.cpp-dgx-main-b9071-b417d55/src/llama-kv-cache.cpp:374:23: warning: unused variable ‘v’ [-Wunused-variable]
  374 |         ggml_tensor * v = has_v ? ggml_new_tensor_3d(ctx, layer_type_v, n_embd_v_gqa, kv_size, n_stream) : nullptr;
      |                       ^
[ 36%] Building CXX object src/CMakeFiles/llama.dir/llama-memory.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-memory-hybrid.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-memory-hybrid-iswa.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-memory-recurrent.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-mmap.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-model-loader.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-model-saver.cpp.o
[ 37%] Building CXX object src/CMakeFiles/llama.dir/llama-model.cpp.o
[ 38%] Building CXX object src/CMakeFiles/llama.dir/llama-quant.cpp.o
[ 38%] Building CXX object src/CMakeFiles/llama.dir/llama-sampler.cpp.o
[ 38%] Building CXX object src/CMakeFiles/llama.dir/llama-vocab.cpp.o
[ 38%] Building CXX object src/CMakeFiles/llama.dir/unicode-data.cpp.o
[ 38%] Building CXX object src/CMakeFiles/llama.dir/unicode.cpp.o
[ 38%] Building CXX object src/CMakeFiles/llama.dir/models/afmoe.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/apertus.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/arcee.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/arctic.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/arwkv7.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/baichuan.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/bailingmoe.cpp.o
[ 39%] Building CXX object src/CMakeFiles/llama.dir/models/bailingmoe2.cpp.o
[ 40%] Building CXX object src/CMakeFiles/llama.dir/models/bert.cpp.o
[ 40%] Building CXX object src/CMakeFiles/llama.dir/models/bitnet.cpp.o
[ 40%] Building CXX object src/CMakeFiles/llama.dir/models/bloom.cpp.o
[ 40%] Building CXX object src/CMakeFiles/llama.dir/models/chameleon.cpp.o
[ 40%] Building CXX object src/CMakeFiles/llama.dir/models/chatglm.cpp.o
[ 40%] Building CXX object src/CMakeFiles/llama.dir/models/codeshell.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/cogvlm.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/cohere2-iswa.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/command-r.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/dbrx.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/deci.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/deepseek.cpp.o
[ 41%] Building CXX object src/CMakeFiles/llama.dir/models/deepseek2.cpp.o
[ 42%] Building CXX object src/CMakeFiles/llama.dir/models/delta-net-base.cpp.o
[ 42%] Building CXX object src/CMakeFiles/llama.dir/models/dots1.cpp.o
[ 42%] Building CXX object src/CMakeFiles/llama.dir/models/dream.cpp.o
[ 42%] Building CXX object src/CMakeFiles/llama.dir/models/ernie4-5-moe.cpp.o
[ 42%] Building CXX object src/CMakeFiles/llama.dir/models/ernie4-5.cpp.o
[ 42%] Building CXX object src/CMakeFiles/llama.dir/models/eurobert.cpp.o
[ 43%] Building CXX object src/CMakeFiles/llama.dir/models/exaone-moe.cpp.o
[ 43%] Building CXX object src/CMakeFiles/llama.dir/models/exaone.cpp.o
[ 43%] Building CXX object src/CMakeFiles/llama.dir/models/exaone4.cpp.o
[ 43%] Building CXX object src/CMakeFiles/llama.dir/models/falcon-h1.cpp.o
[ 43%] Building CXX object src/CMakeFiles/llama.dir/models/falcon.cpp.o
[ 43%] Building CXX object src/CMakeFiles/llama.dir/models/gemma-embedding.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/gemma.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/gemma2-iswa.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/gemma3.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/gemma3n-iswa.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/gemma4-iswa.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/glm4-moe.cpp.o
[ 44%] Building CXX object src/CMakeFiles/llama.dir/models/glm4.cpp.o
[ 45%] Building CXX object src/CMakeFiles/llama.dir/models/gpt2.cpp.o
[ 45%] Building CXX object src/CMakeFiles/llama.dir/models/gptneox.cpp.o
[ 45%] Building CXX object src/CMakeFiles/llama.dir/models/granite-hybrid.cpp.o
[ 45%] Building CXX object src/CMakeFiles/llama.dir/models/granite.cpp.o
[ 45%] Building CXX object src/CMakeFiles/llama.dir/models/grok.cpp.o
[ 45%] Building CXX object src/CMakeFiles/llama.dir/models/grovemoe.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/hunyuan-dense.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/hunyuan-moe.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/internlm2.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/jais.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/jais2.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/jamba.cpp.o
[ 46%] Building CXX object src/CMakeFiles/llama.dir/models/kimi-linear.cpp.o
[ 47%] Building CXX object src/CMakeFiles/llama.dir/models/lfm2.cpp.o
[ 47%] Building CXX object src/CMakeFiles/llama.dir/models/llada-moe.cpp.o
[ 47%] Building CXX object src/CMakeFiles/llama.dir/models/llada.cpp.o
[ 47%] Building CXX object src/CMakeFiles/llama.dir/models/llama-iswa.cpp.o
[ 47%] Building CXX object src/CMakeFiles/llama.dir/models/llama.cpp.o
[ 47%] Building CXX object src/CMakeFiles/llama.dir/models/maincoder.cpp.o
[ 48%] Building CXX object src/CMakeFiles/llama.dir/models/mamba-base.cpp.o
[ 48%] Building CXX object src/CMakeFiles/llama.dir/models/mamba.cpp.o
[ 48%] Building CXX object src/CMakeFiles/llama.dir/models/mimo2-iswa.cpp.o
[ 48%] Building CXX object src/CMakeFiles/llama.dir/models/minicpm3.cpp.o
[ 48%] Building CXX object src/CMakeFiles/llama.dir/models/minimax-m2.cpp.o
[ 48%] Building CXX object src/CMakeFiles/llama.dir/models/mistral3.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/modern-bert.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/mpt.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/nemotron-h.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/nemotron.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/neo-bert.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/olmo.cpp.o
[ 49%] Building CXX object src/CMakeFiles/llama.dir/models/olmo2.cpp.o
[ 50%] Building CXX object src/CMakeFiles/llama.dir/models/olmoe.cpp.o
[ 50%] Building CXX object src/CMakeFiles/llama.dir/models/openai-moe-iswa.cpp.o
[ 50%] Building CXX object src/CMakeFiles/llama.dir/models/openelm.cpp.o
[ 50%] Building CXX object src/CMakeFiles/llama.dir/models/orion.cpp.o
[ 50%] Building CXX object src/CMakeFiles/llama.dir/models/paddleocr.cpp.o
[ 50%] Building CXX object src/CMakeFiles/llama.dir/models/pangu-embedded.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/phi2.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/phi3.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/plamo.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/plamo2.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/plamo3.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/plm.cpp.o
[ 51%] Building CXX object src/CMakeFiles/llama.dir/models/qwen.cpp.o
[ 52%] Building CXX object src/CMakeFiles/llama.dir/models/qwen2.cpp.o
[ 52%] Building CXX object src/CMakeFiles/llama.dir/models/qwen2moe.cpp.o
[ 52%] Building CXX object src/CMakeFiles/llama.dir/models/qwen2vl.cpp.o
[ 52%] Building CXX object src/CMakeFiles/llama.dir/models/qwen3.cpp.o
[ 52%] Building CXX object src/CMakeFiles/llama.dir/models/qwen35.cpp.o
[ 52%] Building CXX object src/CMakeFiles/llama.dir/models/qwen35moe.cpp.o
[ 53%] Building CXX object src/CMakeFiles/llama.dir/models/qwen3moe.cpp.o
[ 53%] Building CXX object src/CMakeFiles/llama.dir/models/qwen3next.cpp.o
[ 53%] Building CXX object src/CMakeFiles/llama.dir/models/qwen3vl-moe.cpp.o
[ 53%] Building CXX object src/CMakeFiles/llama.dir/models/qwen3vl.cpp.o
[ 53%] Building CXX object src/CMakeFiles/llama.dir/models/refact.cpp.o
[ 53%] Building CXX object src/CMakeFiles/llama.dir/models/rnd1.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/rwkv6-base.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/rwkv6.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/rwkv6qwen2.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/rwkv7-base.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/rwkv7.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/seed-oss.cpp.o
[ 54%] Building CXX object src/CMakeFiles/llama.dir/models/smallthinker.cpp.o
[ 55%] Building CXX object src/CMakeFiles/llama.dir/models/smollm3.cpp.o
[ 55%] Building CXX object src/CMakeFiles/llama.dir/models/stablelm.cpp.o
[ 55%] Building CXX object src/CMakeFiles/llama.dir/models/starcoder.cpp.o
[ 55%] Building CXX object src/CMakeFiles/llama.dir/models/starcoder2.cpp.o
[ 55%] Building CXX object src/CMakeFiles/llama.dir/models/step35-iswa.cpp.o
[ 55%] Building CXX object src/CMakeFiles/llama.dir/models/t5-dec.cpp.o
[ 56%] Building CXX object src/CMakeFiles/llama.dir/models/t5-enc.cpp.o
[ 56%] Building CXX object src/CMakeFiles/llama.dir/models/wavtokenizer-dec.cpp.o
[ 56%] Building CXX object src/CMakeFiles/llama.dir/models/xverse.cpp.o
[ 56%] Linking CXX shared library ../bin/libllama.so
[ 56%] Built target llama
[ 57%] Building CXX object common/CMakeFiles/common.dir/arg.cpp.o
[ 57%] Building CXX object examples/simple/CMakeFiles/llama-simple.dir/simple.cpp.o
[ 57%] Building C object tests/CMakeFiles/test-c.dir/test-c.c.o
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd.cpp.o
[ 57%] Linking C executable ../bin/test-c
[ 57%] Built target test-c
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd-audio.cpp.o
[ 57%] Linking CXX executable ../../bin/llama-simple
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)30, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)8, (ggml_type)30>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)1, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)8, (ggml_type)1>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)1, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)8, (ggml_type)1>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)1, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)8, (ggml_type)1>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)30, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<64, (ggml_type)8, (ggml_type)30>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<256, (ggml_type)8, (ggml_type)30>(ggml_backend_cuda_context&, ggml_tensor*)'
/usr/bin/ld: ../../bin/libggml-cuda.so.0.9.11: undefined reference to `void ggml_cuda_flash_attn_ext_vec_case<128, (ggml_type)30, (ggml_type)8>(ggml_backend_cuda_context&, ggml_tensor*)'
collect2: error: ld returned 1 exit status
gmake[2]: *** [examples/simple/CMakeFiles/llama-simple.dir/build.make:102: bin/llama-simple] Error 1
gmake[1]: *** [CMakeFiles/Makefile2:4055: examples/simple/CMakeFiles/llama-simple.dir/all] Error 2
gmake[1]: *** Waiting for unfinished jobs....
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd-image.cpp.o
[ 57%] Building CXX object common/CMakeFiles/common.dir/chat-auto-parser-generator.cpp.o
[ 57%] Building CXX object common/CMakeFiles/common.dir/chat-auto-parser-helpers.cpp.o
[ 57%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/mtmd-helper.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/clip.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/cogvlm.cpp.o
[ 58%] Building CXX object common/CMakeFiles/common.dir/chat-diff-analyzer.cpp.o
[ 58%] Building CXX object common/CMakeFiles/common.dir/chat-peg-parser.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/conformer.cpp.o
[ 58%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/dotsocr.cpp.o
[ 59%] Building CXX object common/CMakeFiles/common.dir/chat.cpp.o
[ 59%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/gemma4a.cpp.o
[ 59%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/gemma4v.cpp.o
[ 59%] Building CXX object common/CMakeFiles/common.dir/common.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/glm4v.cpp.o
[ 60%] Building CXX object common/CMakeFiles/common.dir/console.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/hunyuanocr.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/internvl.cpp.o
[ 60%] Building CXX object common/CMakeFiles/common.dir/debug.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/kimivl.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/kimik25.cpp.o
[ 60%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/nemotron-v2-vl.cpp.o
[ 60%] Building CXX object common/CMakeFiles/common.dir/download.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/llama4.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/llava.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/minicpmv.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/paddleocr.cpp.o
[ 61%] Building CXX object common/CMakeFiles/common.dir/hf-cache.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/pixtral.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/qwen2vl.cpp.o
[ 61%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/qwen3vl.cpp.o
[ 62%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/qwen3a.cpp.o
[ 62%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/step3vl.cpp.o
[ 62%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/siglip.cpp.o
[ 63%] Building CXX object common/CMakeFiles/common.dir/json-partial.cpp.o
[ 63%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/whisper-enc.cpp.o
[ 63%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/deepseekocr.cpp.o
[ 63%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/mobilenetv5.cpp.o
[ 64%] Building CXX object tools/mtmd/CMakeFiles/mtmd.dir/models/youtuvl.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/json-schema-to-grammar.cpp.o
[ 64%] Linking CXX shared library ../../bin/libmtmd.so
[ 64%] Built target mtmd
[ 64%] Building CXX object common/CMakeFiles/common.dir/llguidance.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/log.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/ngram-cache.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/ngram-map.cpp.o
[ 64%] Building CXX object common/CMakeFiles/common.dir/ngram-mod.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/peg-parser.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/preset.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/regex-partial.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/reasoning-budget.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/sampling.cpp.o
[ 65%] Building CXX object common/CMakeFiles/common.dir/speculative.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/unicode.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/lexer.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/parser.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/runtime.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/value.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/string.cpp.o
[ 66%] Building CXX object common/CMakeFiles/common.dir/jinja/caps.cpp.o
[ 67%] Building CXX object common/CMakeFiles/common.dir/__/license.cpp.o
[ 67%] Linking CXX static library libcommon.a
[ 67%] Built target common
gmake: *** [Makefile:146: all] Error 2

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions