github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #458] Docker container support #62251

New Issue
Closed
opened 2026-05-03 07:59:48 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-03 07:59:48 -05:00
Owner
Copy Link

Originally created by @philipempl on GitHub (Sep 2, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/458

Hi there,

is it possible to run ./ollama run llama2 in a docker container? I am able to build two docker containers (server and model), the model container connects to the server and loads the llama model, but when I communicate with the llama2 model, I get the following error:

hi
⠋

Error: unexpected end of response

Here is the model Dockerfile I use. The server file looks nearly the same.

FROM golang:1.20 AS source
RUN apt-get update && apt-get install -y cmake git
WORKDIR /app
RUN git clone https://github.com/jmorganca/ollama.git .
RUN go generate ./...
RUN CGO_ENABLED=1 go build -ldflags '-linkmode external -extldflags "-static"' .

FROM alpine
COPY --from=source /app/ollama /bin/ollama
ARG USER=ollama
ARG GROUP=ollama
RUN addgroup -g 1000 $GROUP && adduser -u 1000 -DG $GROUP $USER
USER $USER:$GROUP
ENTRYPOINT ["/bin/ollama"]
CMD ["run", "llama2", "--verbose"]

Thanks a lot for your help.

Best regards,
Philip

Originally created by @philipempl on GitHub (Sep 2, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/458 Hi there, is it possible to run ./ollama run llama2 in a docker container? I am able to build two docker containers (server and model), the model container connects to the server and loads the llama model, but when I communicate with the llama2 model, I get the following error: >>> hi ⠋ Error: unexpected end of response Here is the model Dockerfile I use. The server file looks nearly the same. FROM golang:1.20 AS source RUN apt-get update && apt-get install -y cmake git WORKDIR /app RUN git clone https://github.com/jmorganca/ollama.git . RUN go generate ./... RUN CGO_ENABLED=1 go build -ldflags '-linkmode external -extldflags "-static"' . FROM alpine COPY --from=source /app/ollama /bin/ollama ARG USER=ollama ARG GROUP=ollama RUN addgroup -g 1000 $GROUP && adduser -u 1000 -DG $GROUP $USER USER $USER:$GROUP ENTRYPOINT ["/bin/ollama"] CMD ["run", "llama2", "--verbose"] Thanks a lot for your help. Best regards, Philip
GiteaMirror commented 2026-05-03 07:59:56 -05:00
Author
Owner
Copy Link

@philipempl commented on GitHub (Sep 4, 2023):

ollama | 2023/09/04 18:31:32 ggml_llama.go:295: error starting llama.cpp server: error starting the external llama.cpp server: fork/exec /tmp/llama-2755348604/server: no such file or directory
ollama | [GIN] 2023/09/04 - 18:31:32 | 500 | 15.834125ms | 127.0.0.1 | POST "/api/generate"
ollama |
ollama |
ollama |
ollama |
ollama | 2023/09/04 18:31:32 [Recovery] 2023/09/04 - 18:31:32 panic recovered:
ollama | POST /api/generate HTTP/1.1
ollama | Host: 0.0.0.0:11434
ollama | Accept: application/json
ollama | Accept-Encoding: gzip
ollama | Content-Length: 72
ollama | Content-Type: application/json
ollama | User-Agent: ollama/0.0.0 (arm64 linux) Go/go1.20.7
ollama |
ollama |
ollama |
ollama | runtime error: invalid memory address or nil pointer dereference
ollama | /usr/local/go/src/runtime/panic.go:260 (0x4329f7)
ollama | /usr/local/go/src/runtime/signal_unix.go:841 (0x44ab63)
ollama | /usr/local/go/src/os/exec_unix.go:63 (0x4fefac)
ollama | /usr/local/go/src/os/exec.go:138 (0x6a88c7)
ollama | /usr/local/go/src/os/exec_posix.go:67 (0x6a88b4)
ollama | /usr/local/go/src/os/exec.go:123 (0x6a88b0)
ollama | /usr/local/go/src/os/exec/exec.go:449 (0x6a88ac)
ollama | /app/llm/ggml_llama.go:349 (0x76b543)
ollama | (*llama).Close: llm.Running.Cmd.Cancel()
ollama | /app/llm/ggml_llama.go:296 (0x76b534)
ollama | newLlama: llm.Close()
ollama | /app/llm/llm.go:80 (0x76e6d3)
ollama | New: return newLlama(model, adapters, ggmlRunner(), opts)
ollama | /app/server/routes.go:95 (0xa1c1ef)
ollama | load: llmModel, err := llm.New(model.ModelPath, model.AdapterPaths, opts)
ollama | /app/server/routes.go:173 (0xa1c78f)
ollama | GenerateHandler: if err := load(c.Request.Context(), model, req.Options, sessionDuration); err != nil {
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 (0xa04f7b)
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/recovery.go:102 (0xa04f5c)
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 (0xa0425b)
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/logger.go:240 (0xa04238)
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 (0xa0339b)
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:620 (0xa030c4)
ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:576 (0xa02cc3)
ollama | /usr/local/go/src/net/http/server.go:2936 (0x68271f)
ollama | /usr/local/go/src/net/http/server.go:1995 (0x67e4f7)
ollama | /usr/local/go/src/runtime/asm_arm64.s:1172 (0x465e93)
ollama |
ollama | [GIN] 2023/09/04 - 18:31:38 | 200 | 3.458µs | 127.0.0.1 | HEAD "/"

<!-- gh-comment-id:1705606451 --> @philipempl commented on GitHub (Sep 4, 2023): ollama | 2023/09/04 18:31:32 ggml_llama.go:295: error starting llama.cpp server: error starting the external llama.cpp server: fork/exec /tmp/llama-2755348604/server: no such file or directory ollama | [GIN] 2023/09/04 - 18:31:32 | 500 | 15.834125ms | 127.0.0.1 | POST "/api/generate" ollama | ollama | ollama | ollama | ollama | 2023/09/04 18:31:32 [Recovery] 2023/09/04 - 18:31:32 panic recovered: ollama | POST /api/generate HTTP/1.1 ollama | Host: 0.0.0.0:11434 ollama | Accept: application/json ollama | Accept-Encoding: gzip ollama | Content-Length: 72 ollama | Content-Type: application/json ollama | User-Agent: ollama/0.0.0 (arm64 linux) Go/go1.20.7 ollama | ollama | ollama | ollama | runtime error: invalid memory address or nil pointer dereference ollama | /usr/local/go/src/runtime/panic.go:260 (0x4329f7) ollama | /usr/local/go/src/runtime/signal_unix.go:841 (0x44ab63) ollama | /usr/local/go/src/os/exec_unix.go:63 (0x4fefac) ollama | /usr/local/go/src/os/exec.go:138 (0x6a88c7) ollama | /usr/local/go/src/os/exec_posix.go:67 (0x6a88b4) ollama | /usr/local/go/src/os/exec.go:123 (0x6a88b0) ollama | /usr/local/go/src/os/exec/exec.go:449 (0x6a88ac) ollama | /app/llm/ggml_llama.go:349 (0x76b543) ollama | (*llama).Close: llm.Running.Cmd.Cancel() ollama | /app/llm/ggml_llama.go:296 (0x76b534) ollama | newLlama: llm.Close() ollama | /app/llm/llm.go:80 (0x76e6d3) ollama | New: return newLlama(model, adapters, ggmlRunner(), opts) ollama | /app/server/routes.go:95 (0xa1c1ef) ollama | load: llmModel, err := llm.New(model.ModelPath, model.AdapterPaths, opts) ollama | /app/server/routes.go:173 (0xa1c78f) ollama | GenerateHandler: if err := load(c.Request.Context(), model, req.Options, sessionDuration); err != nil { ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 (0xa04f7b) ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/recovery.go:102 (0xa04f5c) ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 (0xa0425b) ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/logger.go:240 (0xa04238) ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 (0xa0339b) ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:620 (0xa030c4) ollama | /go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:576 (0xa02cc3) ollama | /usr/local/go/src/net/http/server.go:2936 (0x68271f) ollama | /usr/local/go/src/net/http/server.go:1995 (0x67e4f7) ollama | /usr/local/go/src/runtime/asm_arm64.s:1172 (0x465e93) ollama | ollama | [GIN] 2023/09/04 - 18:31:38 | 200 | 3.458µs | 127.0.0.1 | HEAD "/"
GiteaMirror commented 2026-05-03 07:59:58 -05:00
Author
Owner
Copy Link

@priamai commented on GitHub (Sep 5, 2023):

I have a working docker solution I think let me dig my notes!

<!-- gh-comment-id:1706376656 --> @priamai commented on GitHub (Sep 5, 2023): I have a working docker solution I think let me dig my notes!
GiteaMirror commented 2026-05-03 07:59:59 -05:00
Author
Owner
Copy Link

@priamai commented on GitHub (Sep 5, 2023):

This works for me:

#!/bin/bash

docker build . -t ollama
docker run -p 11434:11434 ollama -d


curl -X POST http://localhost:11434/api/pull -d '{"name": "llama2"}'
<!-- gh-comment-id:1706378318 --> @priamai commented on GitHub (Sep 5, 2023): This works for me: ``` #!/bin/bash docker build . -t ollama docker run -p 11434:11434 ollama -d curl -X POST http://localhost:11434/api/pull -d '{"name": "llama2"}' ```
GiteaMirror commented 2026-05-03 08:00:00 -05:00
Author
Owner
Copy Link

@priamai commented on GitHub (Sep 5, 2023):

docker composer file, I think is almost the same.

version: "3.3"
services:
  ollama:
    build:
      context: .
    env_file: .env
    ports:
      - "${HOST_API_PORT:-11434}:${CONTAINER_API_PORT:-11434}"
    stdin_open: true
    tty: true
<!-- gh-comment-id:1706379474 --> @priamai commented on GitHub (Sep 5, 2023): docker composer file, I think is almost the same. ``` version: "3.3" services: ollama: build: context: . env_file: .env ports: - "${HOST_API_PORT:-11434}:${CONTAINER_API_PORT:-11434}" stdin_open: true tty: true ```
GiteaMirror commented 2026-05-03 08:00:01 -05:00
Author
Owner
Copy Link

@philipempl commented on GitHub (Sep 5, 2023):

thanks a lot @priamai for your fast response. I have a few questions about that:

Do you also use the same Dockerfile as i do?
How do you run the commands like "ollama run llama2"?
How do you request api/generate?

Have a nice day :)

<!-- gh-comment-id:1706646281 --> @philipempl commented on GitHub (Sep 5, 2023): thanks a lot @priamai for your fast response. I have a few questions about that: Do you also use the same Dockerfile as i do? How do you run the commands like "ollama run llama2"? How do you request api/generate? Have a nice day :)
GiteaMirror commented 2026-05-03 08:00:02 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Sep 7, 2023):

There's now a Dockerfile that's kept up to date: https://github.com/jmorganca/ollama/blob/main/Dockerfile 🎉

<!-- gh-comment-id:1710182977 --> @jmorganca commented on GitHub (Sep 7, 2023): There's now a Dockerfile that's kept up to date: https://github.com/jmorganca/ollama/blob/main/Dockerfile 🎉
GiteaMirror commented 2026-05-03 08:00:03 -05:00
Author
Owner
Copy Link

@philipempl commented on GitHub (Sep 7, 2023):

@jmorganca Thanks a lot, this Dockerfile works just perfect 🥳 Would it be an option to replace that with the Dockerfile in the main directory?

However, thanks for creating and maintaining this awesome project 🙂

<!-- gh-comment-id:1710567627 --> @philipempl commented on GitHub (Sep 7, 2023): @jmorganca Thanks a lot, this Dockerfile works just perfect 🥳 Would it be an option to replace that with the Dockerfile in the main directory? However, thanks for creating and maintaining this awesome project 🙂
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#62251
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?