From e37651cca06c55151fbce4a5a21b595f7bcfb38a Mon Sep 17 00:00:00 2001 From: jmorganca Date: Sun, 19 May 2024 14:01:52 -0700 Subject: [PATCH] add clip and parallel requests to the todo list --- llama/README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/llama/README.md b/llama/README.md index a19d9c31..e841f6ae 100644 --- a/llama/README.md +++ b/llama/README.md @@ -2,6 +2,8 @@ This package integrates llama.cpp as a Go package that's easy to build with tags for different CPU and GPU processors. +Supported: + - [x] CPU - [x] avx, avx2 - [ ] avx512 @@ -10,6 +12,8 @@ This package integrates llama.cpp as a Go package that's easy to build with tags - [x] Windows ROCm - [ ] Linux CUDA - [ ] Linux ROCm +- [ ] Clip +- [ ] Parallel Requests Extra build steps are required for CUDA and ROCm on Windows since `nvcc` and `hipcc` both require using msvc as the host compiler. For these small dlls are created: