Georgi Gerganov 7cd3de89bf ggml : extend the GGML_SCHED_NO_REALLOC debug logic of the scheduler (llama/17617)

2025-12-12 17:53:14 +02:00

..

ggml-blas

…

ggml-cann

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml-cpu

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml-cuda

llama-graph: avoid expand_forward for fusion (llama/17633)

2025-12-12 17:53:14 +02:00

ggml-hexagon

hexagon: add support for ROPE_NEOX (llama/17458)

2025-12-12 17:53:07 +02:00

ggml-hip

…

ggml-metal

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml-musa

…

ggml-opencl

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml-rpc

rpc : cache and reuse compute graphs (llama/15405)

2025-12-12 17:53:11 +02:00

ggml-sycl

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml-vulkan

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml-webgpu

ggml webgpu: faster matrix multiplication/matrix-vector multiplication (llama/17031)

2025-11-09 23:38:03 +02:00

ggml-zdnn

…

CMakeLists.txt

ggml: fix: macOS build with -DGGML_BACKEND_DL=ON (llama/17581)

2025-12-12 17:53:13 +02:00

ggml-alloc.c

ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (llama/17276)

2025-12-12 17:53:12 +02:00

ggml-backend-impl.h

…

ggml-backend-reg.cpp

…

ggml-backend.cpp

ggml : extend the GGML_SCHED_NO_REALLOC debug logic of the scheduler (llama/17617)

2025-12-12 17:53:14 +02:00

ggml-common.h

…

ggml-impl.h

ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (llama/17063)

2025-11-17 21:05:46 +02:00

ggml-opt.cpp

…

ggml-quants.c

…

ggml-quants.h

…

ggml-threading.cpp

…

ggml-threading.h

…

ggml.c

model: LFM2-VL fixes (llama/17577)

2025-12-12 17:53:14 +02:00

ggml.cpp

…

gguf.cpp

…