8000 llama-cpp-python/docker at main · yangtzelsl/llama-cpp-python · GitHub
[go: up one dir, main page]

Skip to content
{"payload":{"allShortcutsEnabled":false,"path":"docker","repo":{"id":728744394,"defaultBranch":"main","name":"llama-cpp-python","ownerLogin":"yangtzelsl","currentUserCanPush":false,"isFork":true,"isEmpty":false,"createdAt":"2023-12-07T15:45:36.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/33994422?v=4","public":true,"private":false,"isOrgOwned":false},"currentUser":null,"refInfo":{"name":"main","listCacheKey":"v0:1701963939.48662","canEdit":false,"refType":"branch","currentOid":"f3b844ed0a139fc5799d6e515e9d1d063c311f97"},"tree":{"items":[{"name":"cuda_simple","path":"docker/cuda_simple","contentType":"directory"},{"name":"open_llama","path":"docker/open_llama","contentType":"directory"},{"name":"openblas_simple","path":"docker/openblas_simple","contentType":"directory"},{"name":"simple","path":"docker/simple","contentType":"directory"},{"name":"README.md","path":"docker/README.md","contentType":"file"}],"templateDirectorySuggestionUrl":null,"readme":{"displayName":"README.md","richText":"\u003carticle class=\"markdown-body entry-content container-lg\" itemprop=\"text\"\u003e\u003cdiv class=\"markdown-heading\" dir=\"auto\"\u003e\u003ch3 tabindex=\"-1\" class=\"heading-element\" dir=\"auto\"\u003eInstall Docker Server\u003c/h3\u003e\u003ca id=\"user-content-install-docker-server\" class=\"anchor\" aria-label=\"Permalink: Install Docker Server\" href=\"#install-docker-server\"\u003e\u003csvg class=\"octicon octicon-link\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z\"\u003e\u003c/path\u003e\u003c/svg\u003e\u003c/a\u003e\u003c/div\u003e\n\u003cdiv class=\"markdown-alert markdown-alert-important\" dir=\"auto\"\u003e\u003cp class=\"markdown-alert-title\" dir=\"auto\"\u003e\u003csvg class=\"octicon octicon-report mr-2\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"M0 1.75C0 .784.784 0 1.75 0h12.5C15.216 0 16 .784 16 1.75v9.5A1.75 1.75 0 0 1 14.25 13H8.06l-2.573 2.573A1.458 1.458 0 0 1 3 14.543V13H1.75A1.75 1.75 0 0 1 0 11.25Zm1.75-.25a.25.25 0 0 0-.25.25v9.5c0 .138.112.25.25.25h2a.75.75 0 0 1 .75.75v2.19l2.72-2.72a.749.749 0 0 1 .53-.22h6.5a.25.25 0 0 0 .25-.25v-9.5a.25.25 0 0 0-.25-.25Zm7 2.25v2.5a.75.75 0 0 1-1.5 0v-2.5a.75.75 0 0 1 1.5 0ZM9 9a1 1 0 1 1-2 0 1 1 0 0 1 2 0Z\"\u003e\u003c/path\u003e\u003c/svg\u003eImportant\u003c/p\u003e\u003cp dir=\"auto\"\u003eThis was tested with Docker running on Linux. \u003cbr\u003eIf you can get it working on Windows or MacOS, please update this \u003ccode\u003eREADME.md\u003c/code\u003e with a PR!\u003cbr\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003cp dir=\"auto\"\u003e\u003ca href=\"https://docs.docker.com/engine/install\" rel=\"nofollow\"\u003eInstall Docker Engine\u003c/a\u003e\u003c/p\u003e\n\u003cdiv class=\"markdown-heading\" dir=\"auto\"\u003e\u003ch2 tabindex=\"-1\" class=\"heading-element\" dir=\"auto\"\u003eSimple Dockerfiles for building the llama-cpp-python server with external model bin files\u003c/h2\u003e\u003ca id=\"user-content-simple-dockerfiles-for-building-the-llama-cpp-python-server-with-external-model-bin-files\" class=\"anchor\" aria-label=\"Permalink: Simple Dockerfiles for building the llama-cpp-python server with external model bin files\" href=\"#simple-dockerfiles-for-building-the-llama-cpp-python-server-with-external-model-bin-files\"\u003e\u003csvg class=\"octicon octicon-link\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z\"\u003e\u003c/path\u003e\u003c/svg\u003e\u003c/a\u003e\u003c/div\u003e\n\u003cdiv class=\"markdown-heading\" dir=\"auto\"\u003e\u003ch3 tabindex=\"-1\" class=\"heading-element\" dir=\"auto\"\u003eopenblas_simple\u003c/h3\u003e\u003ca id=\"user-content-openblas_simple\" class=\"anchor\" aria-label=\"Permalink: openblas_simple\" href=\"#openblas_simple\"\u003e\u003csvg class=\"octicon octicon-link\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z\"\u003e\u003c/path\u003e\u003c/svg\u003e\u003c/a\u003e\u003c/div\u003e\n\u003cp dir=\"auto\"\u003eA simple Dockerfile for non-GPU OpenBLAS, where the model is located outside the Docker image:\u003c/p\u003e\n\u003cdiv class=\"snippet-clipboard-content notranslate position-relative overflow-auto\" data-snippet-clipboard-copy-content=\"cd ./openblas_simple\ndocker build -t openblas_simple .\ndocker run --cap-add SYS_RESOURCE -e USE_MLOCK=0 -e MODEL=/var/model/\u0026lt;model-path\u0026gt; -v \u0026lt;model-root-path\u0026gt;:/var/model -t openblas_simple\"\u003e\u003cpre class=\"notranslate\"\u003e\u003ccode\u003ecd ./openblas_simple\ndocker build -t openblas_simple .\ndocker run --cap-add SYS_RESOURCE -e USE_MLOCK=0 -e MODEL=/var/model/\u0026lt;model-path\u0026gt; -v \u0026lt;model-root-path\u0026gt;:/var/model -t openblas_simple\n\u003c/code\u003e\u003c/pre\u003e\u003c/div\u003e\n\u003cp dir=\"auto\"\u003ewhere \u003ccode\u003e\u0026lt;model-root-path\u0026gt;/\u0026lt;model-path\u0026gt;\u003c/code\u003e is the full path to the model file on the Docker host system.\u003c/p\u003e\n\u003cdiv class=\"markdown-heading\" dir=\"auto\"\u003e\u003ch3 tabindex=\"-1\" class=\"heading-element\" dir=\"auto\"\u003ecuda_simple\u003c/h3\u003e\u003ca id=\"user-content-cuda_simple\" class=\"anchor\" aria-label=\"Permalink: cuda_simple\" href=\"#cuda_simple\"\u003e\u003csvg class=\"octicon octicon-link\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z\"\u003e\u003c/path\u003e\u003c/svg\u003e\u003c/a\u003e\u003c/div\u003e\n\u003cdiv class=\"markdown-alert markdown-alert-warning\" dir=\"auto\"\u003e\u003cp class=\"markdown-alert-title\" dir=\"auto\"\u003e\u003csvg class=\"octicon octicon-alert mr-2\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"M6.457 1.047c.659-1.234 2.427-1.234 3.086 0l6.082 11.378A1.75 1.75 0 0 1 14.082 15H1.918a1.75 1.75 0 0 1-1.543-2.575Zm1.763.707a.25.25 0 0 0-.44 0L1.698 13.132a.25.25 0 0 0 .22.368h12.164a.25.25 0 0 0 .22-.368Zm.53 3.996v2.5a.75.75 0 0 1-1.5 0v-2.5a.75.75 0 0 1 1.5 0ZM9 11a1 1 0 1 1-2 0 1 1 0 0 1 2 0Z\"\u003e\u003c/path\u003e\u003c/svg\u003eWarning\u003c/p\u003e\u003cp dir=\"auto\"\u003eNvidia GPU CuBLAS support requires an Nvidia GPU with sufficient VRAM (approximately as much as the size in the table below) and Docker Nvidia support (see \u003ca href=\"https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html\" rel=\"nofollow\"\u003econtainer-toolkit/install-guide\u003c/a\u003e) \u003cbr\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003cp dir=\"auto\"\u003eA simple Dockerfile for CUDA-accelerated CuBLAS, where the model is located outside the Docker image:\u003c/p\u003e\n\u003cdiv class=\"snippet-clipboard-content notranslate position-relative overflow-auto\" data-snippet-clipboard-copy-content=\"cd ./cuda_simple\ndocker build -t cuda_simple .\ndocker run --gpus=all --cap-add SYS_RESOURCE -e USE_MLOCK=0 -e MODEL=/var/model/\u0026lt;model-path\u0026gt; -v \u0026lt;model-root-path\u0026gt;:/var/model -t cuda_simple\"\u003e\u003cpre class=\"notranslate\"\u003e\u003ccode\u003ecd ./cuda_simple\ndocker build -t cuda_simple .\ndocker run --gpus=all --cap-add SYS_RESOURCE -e USE_MLOCK=0 -e MODEL=/var/model/\u0026lt;model-path\u0026gt; -v \u0026lt;model-root-path\u0026gt;:/var/model -t cuda_simple\n\u003c/code\u003e\u003c/pre\u003e\u003c/div\u003e\n\u003cp dir=\"auto\"\u003ewhere \u003ccode\u003e\u0026lt;model-root-path\u0026gt;/\u0026lt;model-path\u0026gt;\u003c/code\u003e is the full path to the model file on the Docker host system.\u003c/p\u003e\n\u003chr\u003e\n\u003cdiv class=\"markdown-heading\" dir=\"auto\"\u003e\u003ch3 tabindex=\"-1\" class=\"heading-element\" dir=\"auto\"\u003e\"Open-Llama-in-a-box\"\u003c/h3\u003e\u003ca id=\"user-content-open-llama-in-a-box\" class=\"anchor\" aria-label=\"Permalink: \u0026quot;Open-Llama-in-a-box\u0026quot;\" href=\"#open-llama-in-a-box\"\u003e\u003csvg class=\"octicon octicon-link\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z\"\u003e\u003c/path\u003e\u003c/svg\u003e\u003c/a\u003e\u003c/div\u003e\n\u003cp dir=\"auto\"\u003eDownload an Apache V2.0 licensed 3B params Open LLaMA model and install into a Docker image that runs an OpenBLAS-enabled llama-cpp-python server:\u003c/p\u003e\n\u003cdiv class=\"snippet-clipboard-content notranslate position-relative overflow-auto\" data-snippet-clipboard-copy-content=\"$ cd ./open_llama\n./build.sh\n./start.sh\"\u003e\u003cpre class=\"notranslate\"\u003e\u003ccode\u003e$ cd ./open_llama\n./build.sh\n./start.sh\n\u003c/code\u003e\u003c/pre\u003e\u003c/div\u003e\n\u003cdiv class=\"markdown-heading\" dir=\"auto\"\u003e\u003ch3 tabindex=\"-1\" class=\"heading-element\" dir=\"auto\"\u003eManually choose your own Llama model from Hugging Face\u003c/h3\u003e\u003ca id=\"user-content-manually-choose-your-own-llama-model-from-hugging-face\" class=\"anchor\" aria-label=\"Permalink: Manually choose your own Llama model from Hugging Face\" href=\"#manually-choose-your-own-llama-model-from-hugging-face\"\u003e\u003csvg class=\"octicon octicon-link\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z\"\u003e\u003c/path\u003e\u003c/svg\u003e\u003c/a\u003e\u003c/div\u003e\n\u003cp dir=\"auto\"\u003e\u003ccode\u003epython3 ./hug_model.py -a TheBloke -t llama\u003c/code\u003e\nYou should now have a model in the current directory and \u003ccode\u003emodel.bin\u003c/code\u003e symlinked to it for the subsequent Docker build and copy step. e.g.\u003c/p\u003e\n\u003cdiv class=\"snippet-clipboard-content notranslate position-relative overflow-auto\" data-snippet-clipboard-copy-content=\"docker $ ls -lh *.bin\n-rw-rw-r-- 1 user user 4.8G May 23 18:30 \u0026lt;downloaded-model-file\u0026gt;q5_1.bin\nlrwxrwxrwx 1 user user 24 May 23 18:30 model.bin -\u0026gt; \u0026lt;downloaded-model-file\u0026gt;q5_1.bin\"\u003e\u003cpre class=\"notranslate\"\u003e\u003ccode\u003edocker $ ls -lh *.bin\n-rw-rw-r-- 1 user user 4.8G May 23 18:30 \u0026lt;downloaded-model-file\u0026gt;q5_1.bin\nlrwxrwxrwx 1 user user 24 May 23 18:30 model.bin -\u0026gt; \u0026lt;downloaded-model-file\u0026gt;q5_1.bin\n\u003c/code\u003e\u003c/pre\u003e\u003c/div\u003e\n\u003cdiv class=\"markdown-alert markdown-alert-note\" dir=\"auto\"\u003e\u003cp class=\"markdown-alert-title\" dir=\"auto\"\u003e\u003csvg class=\"octicon octicon-info mr-2\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8Zm8-6.5a6.5 6.5 0 1 0 0 13 6.5 6.5 0 0 0 0-13ZM6.5 7.75A.75.75 0 0 1 7.25 7h1a.75.75 0 0 1 .75.75v2.75h.25a.75.75 0 0 1 0 1.5h-2a.75.75 0 0 1 0-1.5h.25v-2h-.25a.75.75 0 0 1-.75-.75ZM8 6a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z\"\u003e\u003c/path\u003e\u003c/svg\u003eNote\u003c/p\u003e\u003cp dir=\"auto\"\u003eMake sure you have enough disk space to download the model. As the model is then copied into the image you will need at least\n\u003cstrong\u003eTWICE\u003c/strong\u003e as much disk space as the size of the model:\u003cbr\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003cmarkdown-accessiblity-table\u003e\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"right\"\u003eModel\u003c/th\u003e\n\u003cth align=\"right\"\u003eQuantized size\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"right\"\u003e3B\u003c/td\u003e\n\u003ctd align=\"right\"\u003e3 GB\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"right\"\u003e7B\u003c/td\u003e\n\u003ctd align=\"right\"\u003e5 GB\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"right\"\u003e13B\u003c/td\u003e\n\u003ctd align=\"right\"\u003e10 GB\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"right\"\u003e33B\u003c/td\u003e\n\u003ctd align=\"right\"\u003e25 GB\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"right\"\u003e65B\u003c/td\u003e\n\u003ctd align=\"right\"\u003e50 GB\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\u003c/markdown-accessiblity-table\u003e\n\u003cdiv class=\"markdown-alert markdown-alert-note\" dir=\"auto\"\u003e\u003cp class=\"markdown-alert-title\" dir=\"auto\"\u003e\u003csvg class=\"octicon octicon-info mr-2\" viewBox=\"0 0 16 16\" version=\"1.1\" width=\"16\" height=\"16\" aria-hidden=\"true\"\u003e\u003cpath d=\"M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8Zm8-6.5a6.5 6.5 0 1 0 0 13 6.5 6.5 0 0 0 0-13ZM6.5 7.75A.75.75 0 0 1 7.25 7h1a.75.75 0 0 1 .75.75v2.75h.25a.75.75 0 0 1 0 1.5h-2a.75.75 0 0 1 0-1.5h.25v-2h-.25a.75.75 0 0 1-.75-.75ZM8 6a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z\"\u003e\u003c/path\u003e\u003c/svg\u003eNote\u003c/p\u003e\u003cp dir=\"auto\"\u003eIf you want to pass or tune additional parameters, customise \u003ccode\u003e./start_server.sh\u003c/code\u003e before running \u003ccode\u003edocker build ...\u003c/code\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003c/article\u003e","errorMessage":null,"headerInfo":{"toc":[{"level":3,"text":"Install Docker Server","anchor":"install-docker-server","htmlText":"Install Docker Server"},{"level":2,"text":"Simple Dockerfiles for building the llama-cpp-python server with external model bin files","anchor":"simple-dockerfiles-for-building-the-llama-cpp-python-server-with-external-model-bin-files","htmlText":"Simple Dockerfiles for building the llama-cpp-python server with external model bin files"},{"level":3,"text":"openblas_simple","anchor":"openblas_simple","htmlText":"openblas_simple"},{"level":3,"text":"cuda_simple","anchor":"cuda_simple","htmlText":"cuda_simple"},{"level":3,"text":"\"Open-Llama-in-a-box\"","anchor":"open-llama-in-a-box","htmlText":"\"Open-Llama-in-a-box\""},{"level":3,"text":"Manually choose your own Llama model from Hugging Face","anchor":"manually-choose-your-own-llama-model-from-hugging-face","htmlText":"Manually choose your own Llama model from Hugging Face"}],"siteNavLoginPath":"/login?return_to=https%3A%2F%2Fgithub.com%2Fyangtzelsl%2Fllama-cpp-python%2Ftree%2Fmain%2Fdocker"}},"totalCount":5,"showBranchInfobar":true},"fileTree":{"":{"items":[{"name":".github","path":".github","contentType":"directory"},{"name":"docker","path":"docker","contentType":"directory"},{"name":"docs","path":"docs","contentType":"directory"},{"name":"examples","path":"examples","contentType":"directory"},{"name":"llama_cpp","path":"llama_cpp","contentType":"directory"},{"name":"tests","path":"tests","contentType":"directory"},{"name":"vendor","path":"vendor","contentType":"directory"},{"name":".dockerignore","path":".dockerignore","contentType":"file"},{"name":".gitignore","path":".gitignore","contentType":"file"},{"name":".gitmodules","path":".gitmodules","contentType":"file"},{"name":".readthedocs.yaml","path":".readthedocs.yaml","contentType":"file"},{"name":"CHANGELOG.md","path":"CHANGELOG.md","contentType":"file"},{"name":"CMakeLists.txt","path":"CMakeLists.txt","contentType":"file"},{"name":"LICENSE.md","path":"LICENSE.md","contentType":"file"},{"name":"Makefile","path":"Makefile","contentType":"file"},{"name":"README.md","path":"README.md","contentType":"file"},{"name":"mkdocs.yml","path":"mkdocs.yml","contentType":"file"},{"name":"pyproject.toml","path":"pyproject.toml","contentType":"file"}],"totalCount":18}},"fileTreeProcessingTime":1.938251,"foldersToFetch":[],"treeExpanded":true,"symbolsExpanded":false,"csrf_tokens":{"/yangtzelsl/llama-cpp-python/branches":{"post":"sxbtqfRbbgAaPqj3-v_2Gt4AZQG122OhLghkxbL7keTNv-J2x0VJpwBUNvJhDqmpAe7QMBoZWFLpyOSEFrEAow"},"/yangtzelsl/llama-cpp-python/branches/fetch_and_merge/main":{"post":"WmqAMaVNnWkfWj2JKOD41cje5lhAM3wYZwCYGekuC32bNs8LsxZeHyODFJ-n21Kn74xy3QFfezeZ7lkC8eCIEg"},"/yangtzelsl/llama-cpp-python/branches/fetch_and_merge/main?discard_changes=true":{"post":"nKENlGPYuqfusQxttkK0CbHt56mH6xKPCnQwvLk2Qz9d_UKudYN50dJoJXs5eR57lr9zLMaHFaD0mvGnofjAUA"}}},"title":"llama-cpp-python/docker at main · yangtzelsl/llama-cpp-python","appPayload":{"helpUrl":"https://docs.github.com","findFileWorkerPath":"/assets-cdn/worker/find-file-worker-263cab1760dd.js","findInFileWorkerPath":"/assets-cdn/worker/find-in-file-worker-1b17b3e7786a.js","githubDevUrl":null,"enabled_features":{"code_nav_ui_events":false,"react_blob_overlay":false,"accessible_code_button":true}}}
0