Skip to content

Instantly share code, notes, and snippets.

@AnttiRae

AnttiRae/gist:dc5c09f40d2474caa959155a88b7426d

Created October 28, 2023 05:51
Show Gist options
  • Save AnttiRae/dc5c09f40d2474caa959155a88b7426d to your computer and use it in GitHub Desktop.
Save AnttiRae/dc5c09f40d2474caa959155a88b7426d to your computer and use it in GitHub Desktop.
Download ZIP
llama-gpt-amd - /run.sh --model 7b --with-rocm
Raw
gistfile1.txt
❯ ./run.sh --model 7b --with-rocm
[+] Building 227.3s (31/31) FINISHED docker:default
=> [llama-gpt-api-rocm-ggml internal] load build definition from ggml.Dockerfile 0.2s
=> => transferring dockerfile: 920B 0.0s
=> [llama-gpt-api-rocm-ggml internal] load .dockerignore 0.2s
=> => transferring context: 2B 0.0s
=> [llama-gpt-ui internal] load build definition from Dockerfile 0.3s
=> => transferring dockerfile: 918B 0.0s
=> [llama-gpt-ui internal] load .dockerignore 0.2s
=> => transferring context: 141B 0.0s
=> [llama-gpt-api-rocm-ggml internal] load metadata for docker.io/rocm/dev-ubuntu-22.04:latest 0.0s
=> [llama-gpt-api-rocm-ggml 1/5] FROM docker.io/rocm/dev-ubuntu-22.04 0.3s
=> [llama-gpt-api-rocm-ggml internal] load build context 0.3s
=> => transferring context: 3.60kB 0.0s
=> [llama-gpt-ui internal] load metadata for ghcr.io/ufoscout/docker-compose-wait:latest 1.5s
=> [llama-gpt-ui internal] load metadata for docker.io/library/node:19-alpine 1.9s
=> [llama-gpt-api-rocm-ggml 2/5] RUN apt-get update && apt-get upgrade -y && apt-get install -y git build-essential python3 python3-pip gcc wget rocm-dev rocm-libs rocblas hipblas && mkdir 167.0s
=> [llama-gpt-ui auth] library/node:pull token for registry-1.docker.io 0.0s
=> [llama-gpt-ui production 1/9] FROM docker.io/library/node:19-alpine@sha256:8ec543d4795e2e85af924a24f8acb039792ae9fe8a42ad5b4bf4c277ab34b62e 11.9s
=> => resolve docker.io/library/node:19-alpine@sha256:8ec543d4795e2e85af924a24f8acb039792ae9fe8a42ad5b4bf4c277ab34b62e 0.1s
=> => sha256:8ec543d4795e2e85af924a24f8acb039792ae9fe8a42ad5b4bf4c277ab34b62e 1.43kB / 1.43kB 0.0s
=> => sha256:d0ba7111bc031323ce2706f8e424afc868db289ba40ff55b05561cf59c123be1 1.16kB / 1.16kB 0.0s
=> => sha256:e2a8cc97f817417787050d381376568c494547f9af9decfca6463dee6db6561c 6.73kB / 6.73kB 0.0s
=> => sha256:8a49fdb3b6a5ff2bd8ec6a86c05b2922a0f7454579ecc07637e94dfd1d0639b6 3.40MB / 3.40MB 1.4s
=> => sha256:1197750296b3abe1d21ffbb3d3ea76df5ba887cf82c8e3284d267cbb2aa1724a 48.15MB / 48.15MB 9.5s
=> => sha256:f352bc07f19b43a8678cc8c8efe162ccb6193ead7af6dd366639a01402d1819e 2.34MB / 2.34MB 3.0s
=> => extracting sha256:8a49fdb3b6a5ff2bd8ec6a86c05b2922a0f7454579ecc07637e94dfd1d0639b6 0.1s
=> => sha256:47be83a79857fb67c4d144471b8301ae6fb874971bfaa60d12dc97ea1355cffe 449B / 449B 2.6s
=> => extracting sha256:1197750296b3abe1d21ffbb3d3ea76df5ba887cf82c8e3284d267cbb2aa1724a 1.4s
=> => extracting sha256:f352bc07f19b43a8678cc8c8efe162ccb6193ead7af6dd366639a01402d1819e 0.0s
=> => extracting sha256:47be83a79857fb67c4d144471b8301ae6fb874971bfaa60d12dc97ea1355cffe 0.0s
=> [llama-gpt-ui] FROM ghcr.io/ufoscout/docker-compose-wait:latest@sha256:ee1b58447dcf9ae2aaf84e5904ffc00ed5a983bf986535b19aeb6f2d4a7ceb8a 3.3s
=> => resolve ghcr.io/ufoscout/docker-compose-wait:latest@sha256:ee1b58447dcf9ae2aaf84e5904ffc00ed5a983bf986535b19aeb6f2d4a7ceb8a 0.1s
=> => sha256:ee1b58447dcf9ae2aaf84e5904ffc00ed5a983bf986535b19aeb6f2d4a7ceb8a 2.38kB / 2.38kB 0.0s
=> => sha256:2ebf0b77a3d10f528b6f924d31a14c49dba25184fbac0f4b6f08c9e26050e3ee 480B / 480B 0.0s
=> => sha256:f50c9bd54f7d6e3caefb9a608e6815bfdb1b2a4b6400d940acc09a744b8d63c2 1.08kB / 1.08kB 0.0s
=> => sha256:ca20d452e2dc7814422d2b5d30b52f34889adac67dec57a3fd50fa4fac8a242c 257.97kB / 257.97kB 3.0s
=> => extracting sha256:ca20d452e2dc7814422d2b5d30b52f34889adac67dec57a3fd50fa4fac8a242c 0.0s
=> [llama-gpt-ui internal] load build context 0.2s
=> => transferring context: 1.30MB 0.1s
=> [llama-gpt-ui production 2/9] WORKDIR /app 0.1s
=> [llama-gpt-ui base 3/3] COPY package*.json ./ 0.2s
=> [llama-gpt-ui dependencies 1/1] RUN npm ci 27.2s
=> [llama-gpt-ui build 1/2] COPY . . 0.2s
=> [llama-gpt-ui build 2/2] RUN npm run build 27.0s
=> [llama-gpt-ui production 3/9] COPY --from=dependencies /app/node_modules ./node_modules 5.7s
=> [llama-gpt-ui production 4/9] COPY --from=build /app/.next ./.next 0.2s
=> [llama-gpt-ui production 5/9] COPY --from=build /app/public ./public 0.1s
=> [llama-gpt-ui production 6/9] COPY --from=build /app/package*.json ./ 0.7s
=> [llama-gpt-ui production 7/9] COPY --from=build /app/next.config.js ./next.config.js 0.1s
=> [llama-gpt-ui production 8/9] COPY --from=build /app/next-i18next.config.js ./next-i18next.config.js 0.1s
=> [llama-gpt-ui production 9/9] COPY --from=ghcr.io/ufoscout/docker-compose-wait:latest /wait /wait 0.1s
=> [llama-gpt-ui] exporting to image 5.7s
=> => exporting layers 5.7s
=> => writing image sha256:be40e19cca3000a22f5a06b616da972ab09af4708bbe17dd70fe97489e4186fd 0.0s
=> => naming to docker.io/library/llama-gpt-amd-llama-gpt-ui 0.0s
=> [llama-gpt-api-rocm-ggml 3/5] COPY . . 0.2s
=> [llama-gpt-api-rocm-ggml 4/5] RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings 9.6s
=> [llama-gpt-api-rocm-ggml 5/5] RUN CMAKE_ARGS="-DLLAMA_HIPBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python==0.1.78 16.0s
=> [llama-gpt-api-rocm-ggml] exporting to image 33.8s
=> => exporting layers 33.8s
=> => writing image sha256:1c6663a2c01288118b12e9af305f8a53528365845197c355c92b5f72b3f835e5 0.0s
=> => naming to docker.io/library/llama-gpt-amd-llama-gpt-api-rocm-ggml 0.0s
[+] Running 3/3
✔ Network llama-gpt-amd_default Created 0.1s
✔ Container llama-gpt-amd-llama-gpt-ui-1 Created 0.1s
✔ Container llama-gpt-amd-llama-gpt-api-rocm-ggml-1 Created 0.1s
Attaching to llama-gpt-amd-llama-gpt-api-rocm-ggml-1, llama-gpt-amd-llama-gpt-ui-1
llama-gpt-amd-llama-gpt-ui-1 | [INFO wait] --------------------------------------------------------
llama-gpt-amd-llama-gpt-ui-1 | [INFO wait] docker-compose-wait 2.12.1
llama-gpt-amd-llama-gpt-ui-1 | [INFO wait] ---------------------------
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] Starting with configuration:
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - Hosts to be waiting for: [llama-gpt-api-rocm-ggml:8000]
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - Paths to be waiting for: []
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - Timeout before failure: 3600 seconds
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - TCP connection timeout before retry: 5 seconds
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - Sleeping time before checking for hosts/paths availability: 0 seconds
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - Sleeping time once all hosts/paths are available: 0 seconds
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] - Sleeping time between retries: 1 seconds
llama-gpt-amd-llama-gpt-ui-1 | [DEBUG wait] --------------------------------------------------------
llama-gpt-amd-llama-gpt-ui-1 | [INFO wait] Checking availability of host [llama-gpt-api-rocm-ggml:8000]
Error response from daemon: could not select device driver "amdgpu" with capabilities: [[gpu]]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment