]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commitdiff
readme : add rpc backend (#12842)
authorGeorgi Gerganov <redacted>
Wed, 9 Apr 2025 07:54:42 +0000 (10:54 +0300)
committerGitHub <redacted>
Wed, 9 Apr 2025 07:54:42 +0000 (10:54 +0300)
README.md

index 95a05e6ed75c1354f236abefa1da755aa30baaeb..e56042f1cb2c9fd9ba737b54c64f5dbeb632a7b7 100644 (file)
--- a/README.md
+++ b/README.md
@@ -9,13 +9,6 @@
 
 Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others) in pure C/C++
 
-> [!IMPORTANT]
-> New `llama.cpp` package location: [ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp/pkgs/container/llama.cpp)
->
-> Update your container URLs to: `ghcr.io/ggml-org/llama.cpp`
->
-> More info: https://github.com/ggml-org/llama.cpp/discussions/11801
-
 ## Recent API changes
 
 - [Changelog for `libllama` API](https://github.com/ggml-org/llama.cpp/issues/9289)
@@ -247,6 +240,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
 | [Vulkan](docs/build.md#vulkan) | GPU |
 | [CANN](docs/build.md#cann) | Ascend NPU |
 | [OpenCL](docs/backend/OPENCL.md) | Adreno GPU |
+| [RPC](https://github.com/ggml-org/llama.cpp/tree/master/examples/rpc) | All |
 
 ## Building the project