Georgi Gerganov 162a455402 metal : reduce command encoding overhead (llama/9698)

2024-10-03 12:22:17 +03:00

..

ggml-alloc.h

Threadpool: take 2 (llama/8672)

2024-09-24 19:45:08 +03:00

ggml-backend.h

ggml/examples: add backend support for numerical optimization (ggml/949)

2024-09-24 19:45:08 +03:00

ggml-blas.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-cann.h

cann: Add host buffer type for Ascend NPU (llama/9406)

2024-09-24 19:45:08 +03:00

ggml-cuda.h

feat: Support Moore Threads GPU (llama/8383)

2024-08-08 22:48:46 +03:00

ggml-kompute.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-metal.h

metal : reduce command encoding overhead (llama/9698)

2024-10-03 12:22:17 +03:00

ggml-rpc.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-sycl.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-vulkan.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml.h

test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)

2024-10-03 12:22:17 +03:00