Skip to content

Releases: unum-cloud/ucall

v0.2.7

29 Mar 09:05
Compare
Choose a tag to compare

0.2.7 (2023-03-29)

Make

  • Stricter versioning in CMake (89a42b7)

Upgrade

v0.2.6

27 Mar 14:15
Compare
Choose a tag to compare

0.2.6 (2023-03-27)

Make

v0.2.5

27 Mar 09:33
Compare
Choose a tag to compare

0.2.5 (2023-03-27)

Make

  • Docs publication permissions (6f057e0)

v0.2.4

27 Mar 08:46
Compare
Choose a tag to compare

0.2.4 (2023-03-27)

Build

  • Add Pipeline for generating docs. (779ca91)

Docs

  • Fix styles and add Github link. (79e8181)
  • Mention stripped release VERSION (fca795a)
  • Mention stripped release VERSION (eb339be)
  • Show examples in docs. (7600c31)

Make

v0.2.3

23 Mar 15:00
Compare
Choose a tag to compare

0.2.3 (2023-03-23)

Make

  • Deprecated release rules (bf75cff)

v0.2.2

23 Mar 13:13
Compare
Choose a tag to compare

0.2.2 (2023-03-23)

Make

  • Python to use latest VERSION (d67079c)

v0.2.1

23 Mar 12:34
Compare
Choose a tag to compare

0.2.1 (2023-03-23)

Make

v0.2.0

23 Mar 12:21
Compare
Choose a tag to compare

0.2.0 (2023-03-23)

Add

  • Benchmark Code (a7b7928)
  • Catching error in python server for posix. (4452a07)
  • FastAPI version of the same benchmark (3c3de53)
  • Positionals for python. Closes #29 (f6cd8c4), closes #29
  • Print server startup info in python too. (7281a00)
  • quiet flag. (51364a7)
  • Semantic Versioning (a7e421a)
  • Use raw TCP for Client instead requests (fcede79)

Build

Docs

  • Add PR template, and editor configs (df753e5)

Fix

Make

Refactor

v0.1.0

16 Mar 06:43
608b6be
Compare
Choose a tag to compare

The three of us - @ishkhan42, @VoVoR, and @ashvardanian have added support for NumPy arrays and Pillow images as RPC arguments, adding a small Client class along the way! The following example shows how to serve UForm multi-modal vision-language transformers in just a few lines of Python, connecting dozens of SIMD-accelerated libraries under the hood for ultimate performance!

from ujrpc.rich_posix import Server
import ufrom

server = Server()
model = uform.get_model('unum-cloud/uform-vl-multilingual')

@server
def vectorize(description: str, photo: PIL.Image.Image) -> numpy.ndarray:
    image = model.preprocess_image(photo)
    tokens = model.preprocess_text(description)
    joint_embedding = model.encode_multimodal(image=image, text=tokens)

    return joint_embedding.cpu().detach().numpy()

A new UKV release and the public rollout of UNSW are also right around the corner!