Johannes Gäßler 7e57b20d53 CUDA: manage NCCL communicators in context (llama/21891) ...

* CUDA: manage NCCL communicators in context

* add check that all backends are CUDA

* remove unused vector, limit init to > 1 GPUs

* fix warnings

* fix cuda device, cache allreduce

2026-04-30 11:29:09 +03:00

..

ggml-alloc.h

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (llama/16653)

2025-12-18 08:20:56 +02:00

ggml-backend.h

CUDA: manage NCCL communicators in context (llama/21891)

2026-04-30 11:29:09 +03:00

ggml-blas.h

ggml : build backends as libraries (llama/10256)

2024-11-20 21:00:08 +02:00

ggml-cann.h

docs : Minor cleanups (llama/19252)

2026-02-08 09:29:10 +02:00

ggml-cpp.h

ggml : fix ggml_gallocr_ptr type (ggml/1205)

2025-05-01 13:29:02 +03:00

ggml-cpu.h

ggml-cpu: FA split across kv for faster TG (llama/19209)

2026-02-08 09:29:10 +02:00

ggml-cuda.h

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-hexagon.h

Add experimental ggml-hexagon backend for the Hexagon NPU (llama/16547)

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

ggml-metal.h

metal : refactor + optimize v2 (llama/15995)

2025-09-20 13:46:10 +03:00

ggml-opencl.h

Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (llama/10693)

2024-12-18 12:52:16 +02:00

ggml-openvino.h

ggml : add OpenVINO backend (llama/15307)

2026-03-16 13:10:15 +02:00

ggml-opt.h

chore : correct typos [no ci] (llama/20041)

2026-03-16 13:10:15 +02:00

ggml-rpc.h

rpc : add native RDMA transport for RPC backend (RoCEv2) (llama/20590)

2026-04-30 11:29:09 +03:00

ggml-sycl.h

ggml : build backends as libraries (llama/10256)

2024-11-20 21:00:08 +02:00

ggml-virtgpu.h

ggml-virtgpu: make the code thread safe (llama/19204)

2026-02-08 09:29:10 +02:00

ggml-vulkan.h

vulkan: Make Vulkan optional at runtime (ggml/11493). (llama/11494)

2025-02-27 08:55:36 +02:00

ggml-webgpu.h

ggml: Add initial WebGPU backend (llama/14521)

2025-07-20 00:23:50 +03:00

ggml-zdnn.h

zdnn: refactor codebase + add docs (llama/16178)

2025-09-29 15:18:09 +03:00

ggml-zendnn.h

ggml-zendnn : add ZenDNN backend for AMD CPUs (llama/17690)

2025-12-12 17:53:21 +02:00

ggml.h

docs: more extensive RoPE documentation [no ci] (llama/21953)

2026-04-30 11:29:09 +03:00

gguf.h

llama: fix llama-model-saver (llama/20503)

2026-03-29 15:04:36 +03:00