Releases: unum-cloud/ucall
Releases · unum-cloud/ucall
v0.2.7
v0.2.6
v0.2.5
v0.2.4
v0.2.3
v0.2.2
v0.2.1
v0.2.0
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
forClient
insteadrequests
(fcede79)
Build
- Add "Make" verb (d9fc1c8)
- Added
Refactor
(abf84ed) - Change Semantic Release Token (6c957d7)
- Fixed updating
VERSION
file. (33c1973) - Remove NPM locking (bc9641a)
- Versioning credentials (a865520)
Docs
- Add PR template, and editor configs (df753e5)
Fix
Client
type mismatching. (554cc11)Client
useContent-Length
for full data. (152ab58)- Break after finding
Content-Length
(e87ad96) - More efficient
pack
(de12e57) - Potential UB. (0948918)
- typos (6265f72)
- typos (70ef816)
Make
- Bump Version (a578774)
Refactor
create_user
with FastAPI (75b42b9)- always generate
id
. (1b81e22) - Benchmark class names (7627273)
- Clean up (dbc789b)
- Clean up (8f262e6)
- Clean up unused params (e10963a)
- grpc params (e03afe5)
- import ordering (395b0cf)
- More practical benchmark. (02691fe)
- Move package.json to assets (bd1c0a1)
- Moved
package.json
to workflows. (15020bd) - prepend
_
to internal functions (86bc25e) - Style (f4d8a92)
- Styling (2d5ec7b)
- Sum -> Trivial Login Service. (5cce6d5)
- test.py (285b966)
- Update python numbers in README. (a845565)
v0.1.0
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!