skygpu
/
skynet
mirror of https://github.com/skygpu/skynet.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
191 Commits
7 Branches
10 Tags
1 MiB
Commit Graph

191 Commits (aa1d52dba0f5c7a813b9e194c786ecb099c107e8)

Author SHA1 Message Date
Guillermo Rodriguez 585d304f86
Add reconnect mechanic to dgpu bus 2023-01-08 07:31:03 -03:00
Guillermo Rodriguez 10e77655c6
Remove rpc heartbeat service and add it to gpu bus 2023-01-07 13:01:03 -03:00
Guillermo Rodriguez 9c7293f84f
Merge pull request #3 from guilledk/heartbeat 
Add simple heartbeat mechanic
 2023-01-07 09:09:03 -03:00
Guillermo Rodriguez 1b42f288bc
Add simple heartbeat mechanic 2023-01-07 09:06:35 -03:00
Guillermo Rodriguez 83465aadaf
Merge pull request #2 from guilledk/fix_rectangular_imgs 
Fix bug where we only supported square imgs on telegram frontend reply
 2023-01-07 09:06:02 -03:00
Guillermo Rodriguez e1dba908e7
Fix bug where we only supported square imgs on telegram frontend reply 2023-01-07 09:05:17 -03:00
Guillermo Rodriguez 064c78874b
Merge pull request #1 from guilledk/protobuf 
Switch from `msgspec` to `protobuf`
 2023-01-07 06:12:07 -03:00
Guillermo Rodriguez afec780286
Bump version number 2023-01-06 22:36:25 -03:00
Guillermo Rodriguez 8e8fb22845
Forgot to add protobuf dep 2023-01-06 22:35:23 -03:00
Guillermo Rodriguez 4ff1dc7a5d
Fix a couple bugs on telegram frontend image deseralization and sending metainfo back 2023-01-06 15:14:39 -03:00
Guillermo Rodriguez 6c1799e342
Switch to protobuf 2023-01-06 14:36:50 -03:00
Guillermo Rodriguez 7c27ee866a
Switch test psycopg2 dep to binary 2022-12-31 11:57:01 -03:00
Guillermo Rodriguez 021e9ce72d
Fix big caption bug, and add logging 2022-12-24 15:38:40 -03:00
Guillermo Rodriguez 07321ee5ee
Add logging 2022-12-24 14:32:17 -03:00
Guillermo Rodriguez e2257b4fb5
Disable private msging with skynet 2022-12-24 12:13:05 -03:00
Guillermo Rodriguez ce5d847565
Add say command to telegram frontend 2022-12-24 11:58:03 -03:00
Guillermo Rodriguez 193f60035d
Woops forgot about redo 2022-12-24 11:54:28 -03:00
Guillermo Rodriguez 820c856e55
Fix image meta and add logging on telgram 2022-12-24 11:49:20 -03:00
Guillermo Rodriguez 2ccae8d08a
Fix telegram frontend bug sending upscaled images based on wrong size 2022-12-24 11:42:30 -03:00
Guillermo Rodriguez 2b0ed25605
Add more logging on msg passing 2022-12-24 11:34:00 -03:00
Guillermo Rodriguez 55781688cd
Testing unlimited msg size 2022-12-24 11:28:17 -03:00
Guillermo Rodriguez 8427eaafd7
Need to add more cmd line params to be able to deploy 2022-12-24 11:20:25 -03:00
Guillermo Rodriguez 0a88995cd5
Missing dep Pillow 2022-12-24 10:55:21 -03:00
Guillermo Rodriguez a656be62b6
Disable torch import on cuda-less runs 2022-12-24 10:54:33 -03:00
Guillermo Rodriguez a9c237b538
Add upscaler 2022-12-24 10:39:40 -03:00
Guillermo Rodriguez 1fc2020ed5
Drop old txt2img.py script 2022-12-21 11:59:20 -03:00
Guillermo Rodriguez cb92aed51c
Finish telegram frontend integration 
Correctly update user stats after a txt2img request
Swap tg_id to BIGINT on database
Refactor help topic system to be more generic
Fix skynet brain cli entry point
Fix multi request rpc session, we werent creating a context on the req side
Fix redo method
DGPU now returns image metadata
Improve error messages brain to frontend
Add version as constant
Add telegram dep to requirements
 2022-12-21 11:53:50 -03:00
Guillermo Rodriguez 896b0f684b
Minor fixes to upscaler cli tool 2022-12-19 12:42:31 -03:00
Guillermo Rodriguez 6bc555f0d6
Add authenticated messaging, also cmd line utils txt2img and upscale 2022-12-19 12:36:02 -03:00
Guillermo Rodriguez f6326ad05c
Rework dgpu client to be single task 
Add a lot of dgpu real image gen tests
Modified docker files and environment to allow for quick test relaunch without image rebuild
Rename package from skynet_bot to skynet
Drop tractor usage cause cuda is oriented to just a single proc managing gpu resources
Add ackwnoledge phase to image request for quick gpu disconnected type scenarios
Add click entry point for dgpu
Add posibility to reuse postgres_db fixture on same session by checking if schema init has been already done
 2022-12-17 11:39:42 -03:00
Guillermo Rodriguez d2e676627a
Add TLS for encrypted comms, next HMAC 2022-12-11 13:06:07 -03:00
Guillermo Rodriguez ece290d805
Remove unused import from tg module and unecesary docker command on db startup 2022-12-11 11:10:17 -03:00
Guillermo Rodriguez 9afb192251
Started making roboust testing fixtures to init fresh db and skynet 
Add simple dgpu worker connection test
Make db connection handler manage schema and table init logic
Keep tweaking dgpu main handler attemtping to fix subactor hangs
Change frontend open rpc logic to return a wrapped rpc_call fn referencing the new socket
Decupled user config request validation from telegram module
Fix next_worker logic, now takes in account multiple tasks per dgpu
Add dgpu_workers and dgpu_next calls
Fixed readme, moved db init code into db module
 2022-12-11 11:02:55 -03:00
Guillermo Rodriguez c3852314a7
Move gpu lifecycle tests to its own file to make torch import optional 2022-12-11 08:38:42 -03:00
Guillermo Rodriguez 139aea67b1
Add gpu worker tests to debug tractor lifecycle stuff also logging 
Minor tweak to cuda docker image
Pin tractor branch
Add triton to cuda reqs
 2022-12-11 08:32:25 -03:00
Guillermo Rodriguez 74d2426793
First decupled architecture, still working on integrating tractor gpu workers 2022-12-10 18:18:03 -03:00
Guillermo Rodriguez 91e0693e65
Add more ais, and start upscaler config and pipeline 2022-12-06 17:50:04 -03:00
Guillermo Rodriguez 3a9e612695
Add 4 new ais, donation command, unknown cmd handler 2022-12-06 09:29:41 -03:00
Guillermo Rodriguez 8bd255717e
Add roles and start working on algo selection, clean up rr code 2022-12-05 19:36:21 -03:00
Guillermo Rodriguez 318a21ac81
Add round robin 2022-12-04 21:31:57 -03:00
Guillermo Rodriguez 563efed3e9
Initial commit 2022-12-04 20:39:43 -03:00