Commit Graph

21 Commits

Author SHA1 Message Date
kingbri
4cc0b59bdc Requirements: Add sse-starlette
Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-10 19:41:08 -04:00
kingbri
2025a1c857 Requirements: Unpin uvicorn
v0.28.0 works now and the underlying errors were fixed.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-10 17:48:43 -04:00
kingbri
e33971859b Requirements: Pin uvicorn
Pin uvicorn due to issues with request disconnection in the latest
version.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-10 01:23:36 -05:00
kingbri
228c227c1e Logging: Switch to loguru
Loguru is a flexible logger that allows for easier hooking and imports
into Rich with no problems. Also makes progress bars stick to the
bottom of the terminal window.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-08 01:00:48 -05:00
kingbri
fe0ff240e7 Progress: Switch to Rich
Rich is a more mature library for displaying progress bars, logging,
and console output. This should help properly align progress bars
within the terminal.

Side note: "We're Rich!"

Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-08 01:00:48 -05:00
kingbri
39617adb65 Requirements: Update Exllamav2
v0.0.15

Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-06 22:29:55 -05:00
kingbri
ccd41d720d Requirements: Bump ExllamaV2
v0.0.14

Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-24 12:26:08 -05:00
kingbri
ea00a6bd45 Requirements: Update Exllamav2
Update to v0.0.13.post2

Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-14 21:51:25 -05:00
kingbri
543a9b68c8 Requirements: Update Exllamav2 to 0.0.13.post1
Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-04 21:25:57 -05:00
kingbri
6eeb62b82c Requirements: Update exllamav2, torch, and FA2
Torch to 2.2, exllamav2 to 0.0.13, FA2 to 2.4.2 on Windows and 2.5.2
on Linux.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-02 23:53:42 -05:00
kingbri
3605067898 Requirements: Don't use torch 2.2
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>
2024-01-29 23:30:10 -05:00
kingbri
ee99349a78 Requirements: Bump exllamav2
0.0.12

Signed-off-by: kingbri <bdashore3@proton.me>
2024-01-22 21:13:31 -05:00
Basil
2460b2f8ef Only try to install one of the EXLv2 wheels
...depending on Python version.
2024-01-02 16:56:39 -08:00
AlpinDale
6a5bbd217c feat: logging (#39)
* add logging

* simplify the logger

* formatting

* final touches

* fix format

* Model: Add log to metrics

Signed-off-by: kingbri <bdashore3@proton.me>

---------

Authored-by: AlpinDale <52078762+AlpinDale@users.noreply.github.com>
2023-12-23 04:33:31 +00:00
kingbri
da69ad8cd3 Requirements: Pin versions for some dependencies
Pydantic and Jinja2 need pinned versions.

Signed-off-by: kingbri <bdashore3@proton.me>
2023-12-19 21:48:04 -05:00
kingbri
51ca1ff396 Tree: Switch to Pydantic 2
Pydantic 2 has more modern methods and stability compared to Pydantic 1

Signed-off-by: kingbri <bdashore3@proton.me>
2023-12-18 23:53:47 -05:00
kingbri
f631dd6ff7 Templates: Switch to Jinja2
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>
2023-12-18 23:53:47 -05:00
kingbri
528d58f841 Requirements: Fix AMD
Signed-off-by: kingbri <bdashore3@proton.me>
2023-12-17 00:45:43 -05:00
kingbri
f196f1177d Requirements: Update exllamav2 to 0.0.11
Signed-off-by: kingbri <bdashore3@proton.me>
2023-12-16 19:33:42 -05:00
kingbri
47176a2a1e Requirements: Fix torch install
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>
2023-12-06 19:04:35 -05:00
kingbri
b83e1b704e Requirements: Split for configurations
Add self-contained requirements for cuda 11.8 and ROCm

Signed-off-by: kingbri <bdashore3@proton.me>
2023-12-06 00:00:30 -05:00