ggml/include
Radoslav Gerganov 4f0730d7f2
rpc : add support for multiple devices (llama/16276)
* rpc : add support for multiple devices

Allow rpc-server to expose multiple devices from a single endpoint.
Change RPC protocol to include device identifier where needed.

closes: #15210

* fixes

* use ggml_backend_reg_t

* address review comments

* fix llama-bench backend report

* address review comments, change device naming

* fix cmd order
2025-10-11 18:01:15 +03:00
..
ggml-alloc.h ggml : upgrade init_tensor API to return a ggml_status (llama/11854) 2025-03-04 21:24:42 +02:00
ggml-backend.h rpc : add support for multiple devices (llama/16276) 2025-10-11 18:01:15 +03:00
ggml-blas.h ggml : build backends as libraries (llama/10256) 2024-11-15 22:51:53 +02:00
ggml-cann.h ggml : build backends as libraries (llama/10256) 2024-11-15 22:51:53 +02:00
ggml-cpp.h ggml : fix ggml_gallocr_ptr type (#1205) 2025-04-30 15:20:40 +02:00
ggml-cpu.h ggml: allow casting between f32 and i32 (llama/15783) 2025-09-20 13:33:50 +03:00
ggml-cuda.h ggml : build backends as libraries (llama/10256) 2024-11-15 22:51:53 +02:00
ggml-metal.h metal : refactor + optimize v2 (llama/15995) 2025-09-20 13:33:50 +03:00
ggml-opencl.h Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (llama/10693) 2024-12-17 19:23:40 +02:00
ggml-opt.h finetune: SGD optimizer, more CLI args (llama/13873) 2025-08-14 14:17:28 +03:00
ggml-rpc.h rpc : add support for multiple devices (llama/16276) 2025-10-11 18:01:15 +03:00
ggml-sycl.h ggml : build backends as libraries (llama/10256) 2024-11-15 22:51:53 +02:00
ggml-vulkan.h vulkan: Make Vulkan optional at runtime (#11493). (llama/11494) 2025-02-12 22:00:20 +02:00
ggml-webgpu.h ggml: Add initial WebGPU backend (llama/14521) 2025-07-19 17:47:23 +03:00
ggml-zdnn.h zdnn: refactor codebase + add docs (llama/16178) 2025-09-25 11:56:34 +03:00
ggml.h ggml webgpu: add support for soft_max, optimize rms_norm (llama/16357) 2025-10-11 17:57:54 +03:00
gguf.h GGUF: C++ refactor, backend support, misc fixes (skip) (llama/11030) 2025-01-14 09:36:36 +02:00