Commit graph

15 commits

Author SHA1 Message Date
Ashwin Bharambe
49ce36426f Make llama model download error message a bit better 2024-09-14 08:06:55 -07:00
sisminnmaw
49f2bbbaeb
fixed bug in download not enough disk space condition (#35)
bug:
used undeclared variable in download.py.
when the disk space not enough NameError occured.
2024-08-22 08:10:47 -07:00
Ashwin Bharambe
face3ceff1 suppress warning in CLI 2024-08-21 12:25:39 -07:00
Dalton Flanagan
270b5502d7 broaden URL match in download for older model families 2024-08-21 12:11:11 -04:00
Ashwin Bharambe
e08e963f86 Add --manifest-file option to argparser 2024-08-19 18:26:56 -07:00
Ashwin Bharambe
5e072d0780 Add a --manifest-file option to llama download 2024-08-17 10:08:42 -07:00
Dalton Flanagan
b311dcd143 formatting 2024-08-14 17:03:43 -04:00
dltn
432957d6b6 fix typo 2024-08-13 11:39:57 -07:00
Ashwin Bharambe
e830814399
Introduce Llama stack distributions (#22)
* Add distribution CLI scaffolding

* More progress towards `llama distribution install`

* getting closer to a distro definition, distro install + configure works

* Distribution server now functioning

* read existing configuration, save enums properly

* Remove inference uvicorn server entrypoint and llama inference CLI command

* updated dependency and client model name

* Improved exception handling

* local imports for faster cli

* undo a typo, add a passthrough distribution

* implement full-passthrough in the server

* add safety adapters, configuration handling, server + clients

* cleanup, moving stuff to common, nuke utils

* Add a Path() wrapper at the earliest place

* fixes

* Bring agentic system api to toolchain

Add adapter dependencies and resolve adapters using a topological sort

* refactor to reduce size of `agentic_system`

* move straggler files and fix some important existing bugs

* ApiSurface -> Api

* refactor a method out

* Adapter -> Provider

* Make each inference provider into its own subdirectory

* installation fixes

* Rename Distribution -> DistributionSpec, simplify RemoteProviders

* dict key instead of attr

* update inference config to take model and not model_dir

* Fix passthrough streaming, send headers properly not part of body :facepalm

* update safety to use model sku ids and not model dirs

* Update cli_reference.md

* minor fixes

* add DistributionConfig, fix a bug in model download

* Make install + start scripts do proper configuration automatically

* Update CLI_reference

* Nuke fp8_requirements, fold fbgemm into common requirements

* Update README, add newline between API surface configurations

* Refactor download functionality out of the Command so can be reused

* Add `llama model download` alias for `llama download`

* Show message about checksum file so users can check themselves

* Simpler intro statements

* get ollama working

* Reduce a bunch of dependencies from toolchain

Some improvements to the distribution install script

* Avoid using `conda run` since it buffers everything

* update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes

* add validation for configuration input

* resort imports

* make optional subclasses default to yes for configuration

* Remove additional_pip_packages; move deps to providers

* for inline make 8b model the default

* Add scripts to MANIFEST

* allow installing from test.pypi.org

* Fix #2 to help with testing packages

* Must install llama-models at that same version first

* fix PIP_ARGS

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Hardik Shah <hjshah@meta.com>
2024-08-08 13:38:41 -07:00
Ashwin Bharambe
09cf3fe78b Use new definitions of Model / SKU 2024-07-31 22:44:35 -07:00
Ashwin Bharambe
1bc81eae7b update toolchain to work with updated imports from llama_models 2024-07-30 17:52:57 -07:00
Ashwin Bharambe
23014ea4d1 Add hacks because Cloudfront config limits on the 405b model files 2024-07-30 13:46:47 -07:00
Ashwin Bharambe
040c30ee54 added resumable downloader for downloading models 2024-07-29 23:29:16 -07:00
Lucain
378a2077dd
Update download command (#9) 2024-07-24 16:50:40 -07:00
Ashwin Bharambe
5d5acc8ed5 Initial commit 2024-07-23 08:32:33 -07:00