Pytorch released 2.2 without letting the community know first. Pin
the torch version to 2.1.2 until exllamav2 builds for torch 2.2
Signed-off-by: kingbri <bdashore3@proton.me>
Jinja2 is a lightweight template parser that's used in Transformers
for parsing chat completions. It's much more efficient than Fastchat
and can be imported as part of requirements.
Also allows for unblocking Pydantic's version.
Users now have to provide their own template if needed. A separate
repo may be usable for common prompt template storage.
Signed-off-by: kingbri <bdashore3@proton.me>
Use --extra-index-url to install pytorch. This should be secure enough
since dependency confusion attacks aren't possible with just installing
the torch package.
Signed-off-by: kingbri <bdashore3@proton.me>
sse_starlette kept firing a ping response if it was taking too long
to set an event. Rather than using a hacky workaround, switch to
FastAPI's inbuilt streaming response and construct SSE requests with
a utility function.
This helps the API become more robust and removes an extra requirement.
Signed-off-by: kingbri <bdashore3@proton.me>
Use 2.3.4 from tgw. However, keep the 2.3.3 wheels in requirements
if the newer wheels don't work for now.
Signed-off-by: kingbri <bdashore3@proton.me>
Fastchat requires a lot of dependencies such as transformers, peft,
and accelerate which are heavy. This is not useful unless a user
wants to add a shim for the chat completion endpoint.
Instead, try importing fastchat and notify the console of the error.
Signed-off-by: kingbri <bdashore3@proton.me>
Add support for /v1/completions with the option to use streaming
if needed. Also rewrite API endpoints to use async when possible
since that improves request performance.
Model container parameter names also needed rewrites as well and
set fallback cases to their disabled values.
Signed-off-by: kingbri <bdashore3@proton.me>
YAML is a more flexible format when it comes to configuration. Commandline
arguments are difficult to remember and configure especially for
an API with complicated commandline names. Rather than using half-baked
textfiles, implement a proper config solution.
Also add a progress bar when loading models in the commandline.
Signed-off-by: kingbri <bdashore3@proton.me>
