GitLab

* subprocess improvements

- increase start-up timeout
- when runner fails to start fail rather than timing out
- try runners in order rather than choosing 1 runner
- embed metal runner in metal dir rather than gpu
- refactor logging and error messages

* Update llama.go

* Update llama.go

* simplify by using glob

fix error on upload chunk

implement ProgressWriter

set request.ContentLength

This informs the HTTP client the content length is known and disables
chunked Transfer-Encoding

remove unused

* enable packaging multiple cuda versions
* use nvcc cuda version if available

---------
Co-authored-by: Michael Yang <mxyng@pm.me>

update docker image

* Update API docs
Signed-off-by: Matt Williams <m@technovangelist.com>

* strange TOC was getting auto generated
Signed-off-by: Matt Williams <m@technovangelist.com>

* Update docs/api.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update docs/api.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update docs/api.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update api.md

---------
Signed-off-by: Matt Williams <m@technovangelist.com>
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
Co-authored-by: Michael Chiang <mchiang0610@users.noreply.github.com>

fix: add falcon.go

Mxyng/decode

get model and file type from bin file

* linux gpu support
* handle multiple gpus
* add cuda docker image (#488)
---------
Co-authored-by: Michael Yang <mxyng@pm.me>

fix nil pointer dereference

update dockerignore

fix: retry push on expired token

Go is required and not installed by default.

update dockerfile

remove unused openssh key types