Ashwin Bharambe
9ec46d718d
Show message about checksum file so users can check themselves
2024-08-07 16:17:51 -07:00
Ashwin Bharambe
57402c1a19
Add llama model download
alias for llama download
2024-08-07 16:10:26 -07:00
Ashwin Bharambe
fddaf5c929
Refactor download functionality out of the Command so can be reused
2024-08-07 15:35:12 -07:00
Ashwin Bharambe
68654460f8
Update README, add newline between API surface configurations
2024-08-07 15:14:59 -07:00
Ashwin Bharambe
66412b932b
Nuke fp8_requirements, fold fbgemm into common requirements
2024-08-07 13:58:55 -07:00
Ashwin Bharambe
cc697c59e5
Update CLI_reference
2024-08-06 22:18:02 -07:00
Ashwin Bharambe
e1a7aa4773
Make install + start scripts do proper configuration automatically
2024-08-06 21:53:05 -07:00
Ashwin Bharambe
9e1ca4eeb1
add DistributionConfig, fix a bug in model download
2024-08-06 19:24:52 -07:00
Hardik Shah
ade574a0ef
minor fixes
2024-08-06 18:56:34 -07:00
Hardik Shah
f83b97992c
Update cli_reference.md
2024-08-06 18:55:31 -07:00
Hardik Shah
2a9bdb208b
update safety to use model sku ids and not model dirs
2024-08-06 17:10:05 -07:00
Ashwin Bharambe
a0e61a3c7a
Fix passthrough streaming, send headers properly not part of body :facepalm
2024-08-06 16:39:38 -07:00
Hardik Shah
039861f1c7
update inference config to take model and not model_dir
2024-08-06 15:02:47 -07:00
Ashwin Bharambe
08c3802f45
dict key instead of attr
2024-08-06 14:30:57 -07:00
Ashwin Bharambe
7cc0445517
Rename Distribution -> DistributionSpec, simplify RemoteProviders
2024-08-06 14:05:01 -07:00
Hardik Shah
0a67f3d3e6
installation fixes
2024-08-05 18:04:44 -07:00
Ashwin Bharambe
0de5a807c7
Make each inference provider into its own subdirectory
2024-08-05 16:39:58 -07:00
Ashwin Bharambe
f64668319c
Merge remote-tracking branch 'origin/main' into distros
2024-08-05 14:31:06 -07:00
Ashwin Bharambe
65a9e40174
Adapter -> Provider
2024-08-05 13:42:56 -07:00
Ashwin Bharambe
db3e6dda07
refactor a method out
2024-08-05 13:14:15 -07:00
Ashwin Bharambe
125fdb1b2a
ApiSurface -> Api
2024-08-05 12:46:38 -07:00
Hardik Shah
7664d5701d
update tests and formatting
2024-08-05 12:34:16 -07:00
Ashwin Bharambe
7890921e5c
move straggler files and fix some important existing bugs
2024-08-05 09:30:14 -07:00
Ashwin Bharambe
5e972ece13
refactor to reduce size of agentic_system
2024-08-04 20:34:15 -07:00
Ashwin Bharambe
be19b22391
Bring agentic system api to toolchain
...
Add adapter dependencies and resolve adapters using a topological sort
2024-08-04 17:33:29 -07:00
Ashwin Bharambe
b0e5340645
fixes
2024-08-03 22:16:24 -07:00
Ashwin Bharambe
750202ddd5
Add a Path() wrapper at the earliest place
2024-08-03 21:25:48 -07:00
Ashwin Bharambe
803976df26
cleanup, moving stuff to common, nuke utils
2024-08-03 20:58:00 -07:00
Ashwin Bharambe
fe582a739d
add safety adapters, configuration handling, server + clients
2024-08-03 19:46:59 -07:00
Ashwin Bharambe
9dafa6ad94
implement full-passthrough in the server
2024-08-03 14:15:20 -07:00
Ashwin Bharambe
38fd76f85c
undo a typo, add a passthrough distribution
2024-08-02 20:49:19 -07:00
Hardik Shah
67229f23a4
local imports for faster cli
2024-08-02 16:35:22 -07:00
Ashwin Bharambe
af4710c959
Improved exception handling
2024-08-02 15:52:15 -07:00
Hardik Shah
493f0d99b2
updated dependency and client model name
2024-08-02 15:37:40 -07:00
Hardik Shah
d7a4cdd70d
added options to ollama inference
2024-08-02 14:44:22 -07:00
Ashwin Bharambe
d3e269fcf2
Remove inference uvicorn server entrypoint and llama inference CLI command
2024-08-02 14:18:25 -07:00
Ashwin Bharambe
3bc827cd5f
read existing configuration, save enums properly
2024-08-02 14:09:57 -07:00
Ashwin Bharambe
2cf9915806
Distribution server now functioning
2024-08-02 13:37:40 -07:00
Ashwin Bharambe
041cafbee3
getting closer to a distro definition, distro install + configure works
2024-08-01 23:12:43 -07:00
Ashwin Bharambe
dac2b5a1ed
More progress towards llama distribution install
2024-08-01 16:40:43 -07:00
Ashwin Bharambe
5a583cf16e
Add distribution CLI scaffolding
2024-08-01 14:44:57 -07:00
Ashwin Bharambe
09cf3fe78b
Use new definitions of Model / SKU
2024-07-31 22:44:35 -07:00
Hardik Shah
156bfa0e15
Added Ollama as an inference impl ( #20 )
...
* fix non-streaming api in inference server
* unit test for inline inference
* Added non-streaming ollama inference impl
* add streaming support for ollama inference with tests
* addressing comments
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
2024-07-31 22:08:37 -07:00
Ashwin Bharambe
c253c1c9ad
Begin adding a /safety/run_shield API
2024-07-31 21:57:10 -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
404af06e02
Bump version to 0.0.2
2024-07-29 23:56:41 -07:00
Ashwin Bharambe
7306e6b167
show sampling params in model describe
2024-07-29 23:44:07 -07:00
Ashwin Bharambe
040c30ee54
added resumable downloader for downloading models
2024-07-29 23:29:16 -07:00
Ashwin Bharambe
59574924de
model template --template -> model template --name
2024-07-29 18:21:05 -07:00