nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/ggml/src
History
Nexes the Elder 6198a356a8
Remove deprecated Kompute (Vulkan compute) backend (#2097) 
* Remove broken kompute submodule (ghost - nulled config, corrupted tracking)

The kompute submodule at ggml/src/kompute had its .git/modules/kompute/config
completely zeroed out (null bytes). The submodule was non-functional and is
not used in this fork. Removed:
  - .gitmodules entry
  - .git/config [submodule kompute] section
  - .git/modules/kompute directory
  - ggml/src/kompute working tree

* Extensive removal of all Kompute code and references

Removed the entire Kompute Vulkan compute backend which was
unmaintained and superseded by the Vulkan backend:

Files deleted:
  - ggml/src/ggml-kompute.cpp (Vulkan compute backend implementation)
  - ggml/include/ggml-kompute.h (header)
  - ggml/src/kompute-shaders/ (34 SPIR-V shader source files)

Build system:
  - ggml/CMakeLists.txt: removed GGML_KOMPUTE option
  - ggml/src/CMakeLists.txt: removed compile_shader function, submodule
    add, shader compilation, stamp targets, and all KOMPUTE source refs
  - CMakeLists.txt: removed LLAMA_KOMPUTE deprecation alias

Source code:
  - ggml/src/ggml-backend.cpp: removed kompute reg decl and call
  - ggml/include/ggml.h: removed ggml_cpu_has_kompute() declaration
  - ggml/src/ggml.c: removed ggml_cpu_has_kompute() implementation
    and its reference in ggml_cpu_has_gpublas()
  - src/llama.cpp: removed #include, backend init, buffer type, model
    loading guard, and GPU offload check for Kompute
  - src/llama-model-loader.cpp: removed kompute include
  - common/common.cpp: removed cpu_has_kompute print
  - tests/test-c.c: removed kompute include guard
  - examples/llama-bench/llama-bench.cpp: removed kompute member,
    construction, field serialization, and display string
  - scripts/compare-llama-bench.py: removed kompute from key props,
    bool props, and pretty names
  - scripts/sync-ggml.sh: removed kompute file copy lines
  - scripts/sync-ggml-am.sh: removed kompute path mappings

Git submodule:
  - .gitmodules: removed kompute entry
  - .git/config: removed [submodule kompute] section
  - .git/modules/kompute: removed
  - ggml/src/kompute: removed (working tree)
 		2026-07-08 10:01:01 +02:00
..
cmake Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
ggml-cann Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
ggml-cuda CUDA: fix flash attention for gpt-oss (SWA + attention sinks) on the tile kernels (no-tensor-core GPUs) (#2087) 2026-07-06 17:59:29 +02:00
ggml-sycl Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
iqk GLM-DSA: much better PP performance (CPU-only) (#2074) 2026-07-06 11:57:40 +02:00
llamafile Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
vulkan-shaders Port of Qwen3-VL support from mainline (#883) 2025-11-04 19:20:54 +02:00
CMakeLists.txt Remove deprecated Kompute (Vulkan compute) backend (#2097) 2026-07-08 10:01:01 +02:00
ggml-aarch64.c Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
ggml-aarch64.h Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
ggml-alloc.c Support for Qwen 3.5 MTP (dense models only) (#1698) 2026-04-28 07:47:50 +02:00
ggml-backend-impl.h Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
ggml-backend.cpp Remove deprecated Kompute (Vulkan compute) backend (#2097) 2026-07-08 10:01:01 +02:00
ggml-cann.cpp Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
ggml-common.h Bonsai support (AVX2, generic) (#1570) 2026-04-02 16:54:08 +02:00
ggml-cuda.cu deepseek2 : GLM-DSA sparse attention (lightning indexer), --dsa off by default (#2045) 2026-07-02 09:36:49 +02:00
ggml-impl.h MXFP4 (#682) 2025-08-09 08:40:18 +03:00
ggml-metal.m Fix clang warnings on macOS (#1354) 2026-03-03 16:27:16 +01:00
ggml-metal.metal MXFP4 (#682) 2025-08-09 08:40:18 +03:00
ggml-quants.c Use AVX version VNNI intrinsic when AVX512VNNI not available. (#1748) 2026-05-09 09:02:06 +03:00
ggml-quants.h Quantization options (#1677) 2026-04-23 09:05:39 +02:00
ggml-rpc.cpp server: improve speed of speculative decoding (#1119) 2026-01-10 08:01:22 +02:00
ggml-sycl.cpp Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
ggml-vulkan.cpp Port of Qwen3-VL support from mainline (#883) 2025-11-04 19:20:54 +02:00
ggml.c Remove deprecated Kompute (Vulkan compute) backend (#2097) 2026-07-08 10:01:01 +02:00