Niklas WenzelandYiChen Lv a245a8f48f metal : fix more leaks due to missing autoreleasepools (llama/27883) ...

* metal : fix more leaks due to missing autoreleasepools

* metal : rename variable

* metal : fix another missing pool warning

Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>

---------

Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>

2026-09-04 13:39:38 +03:00

..

ggml-blas

…

ggml-cann

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml-cpu

AVX2: Speed up large batch size prompt processing of IQ models (llama/27402)

2026-09-04 13:39:37 +03:00

ggml-cuda

CUDA: XOR swizzle flash attn K,V smem fp16 tiles (llama/25635)

2026-09-04 13:39:37 +03:00

ggml-et

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml-hexagon

hexagon: fix CPY fence bug (llama/28033)

2026-09-04 13:39:35 +03:00

ggml-hip

…

ggml-metal

metal : fix more leaks due to missing autoreleasepools (llama/27883)

2026-09-04 13:39:38 +03:00

ggml-musa

…

ggml-opencl

opencl: tune the quant paths for Intel Xe-LP GPUs to improve its TG and PP performance (llama/26438)

2026-09-04 13:39:37 +03:00

ggml-openvino

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml-rpc

rpc: avoid serializing buffers from other servers (llama/26500)

2026-09-04 13:39:35 +03:00

ggml-sycl

sycl : support limit max alloc memory within 2GB for host-pinned memory (llama/27559)

2026-09-04 13:39:38 +03:00

ggml-virtgpu

ggml: allow passing alloc dependencies in graph_optimize (llama/27301)

2026-09-04 13:39:33 +03:00

ggml-vulkan

vulkan: tune mat-vec rows for batched inference on Strix Halo (llama/27909)

2026-09-04 13:39:36 +03:00

ggml-webgpu

webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_backend_tensor_get() implementation (llama/28045)

2026-09-04 13:39:37 +03:00

ggml-zdnn

…

ggml-zendnn

CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (llama/26678)

2026-08-21 19:23:26 +03:00

CMakeLists.txt

CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (llama/26678)

2026-08-21 19:23:26 +03:00

ggml-alloc.c

ggml : fix ggml_clamp (llama/27644)

2026-08-25 15:28:56 +03:00

ggml-backend-dl.cpp

…

ggml-backend-dl.h

…

ggml-backend-impl.h

ggml: allow passing alloc dependencies in graph_optimize (llama/27301)

2026-09-04 13:39:33 +03:00

ggml-backend-meta.cpp

ggml-meta: propagate buffer usage and call init on the new tensors (llama/27586)

2026-09-04 13:39:29 +03:00

ggml-backend-reg.cpp

…

ggml-backend.cpp

ggml : add MUL_MAT to the list of ops that may need additional memory (for WebGPU) (llama/28071)

2026-09-04 13:39:36 +03:00

ggml-common.h

AVX2: Speed up large batch size prompt processing of IQ models (llama/27402)

2026-09-04 13:39:37 +03:00

ggml-feats.h

…

ggml-impl.h

…

ggml-opt.cpp

…

ggml-quants.c

…

ggml-quants.h

…

ggml-threading.cpp

…

ggml-threading.h

…

ggml.c

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml.cpp

…

gguf.cpp

…