-
Notifications
You must be signed in to change notification settings - Fork 171
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Livepeer AI Subnet #2959
Livepeer AI Subnet #2959
Conversation
feb3f3e
to
563d199
Compare
d32b1b5 temporarily disables Linux arm64 builds because they fail due to an error related to not being able to find zlib during ffmpeg compilation. This error doesn't occur for amd64 builds so I suspect the issue is related to the amd64 -> arm64 cross-compilation process. I noticed that we compile an arm64 specific version of x264 before compiling ffmpeg - perhaps we have to do something similar with zlib? zlib is currently required as a dependency as of 133050d#diff-4ae778054809274731b9da0c6a5a869c0bd214e92f954a5c9c39181748c2f175 which enabled the png decoder and image2 muxer which are used to demux + decode a sequence of PNG files so they can be encoded into an mp4 file. Ideally, we would replace the PNG demux/decode component by passing tensors (that represent frames) outputted by a model directly from GPU memory to NVENC using torchaudio.StreamWriter, but torchaudio.StreamWriter doesn't support RGB -> YUV conversion on the GPU yet - it can still encode a larger, less-streaming friendly (my understanding is yuv420p is preferred for streaming) RGB output, but I didn't jump to implement this yet due to current limitations. Until this replacement happens, zlib would be a required dependency to support the temporary PNG demux + decode component. |
@yondonfu Weird - on release go-livepeer right now zlib is dynamically linked. I'll have a look. |
* realtime: Add MediaMTX handler to G, and O caps and signaling
This commit ensure that no nil pointer error is thrown when the 'text' request field is not provided. It also applies several small code cleanups.
[AI] Parler Text to Speech
* (a2t) pass duration to orchestrator --------- Co-authored-by: Rick Staa <[email protected]>
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #2959 +/- ##
====================================================
- Coverage 56.71558% 34.96839% -21.74719%
====================================================
Files 92 135 +43
Lines 19693 35901 +16208
====================================================
+ Hits 11169 12554 +1385
- Misses 7917 22641 +14724
- Partials 607 706 +99
... and 19 files with indirect coverage changes Continue to review full report in Codecov by Sentry.
|
This commit removes redundant code in the AI orchestrator server file (i.e. `ai_http.go`) to increase code readability.
This commit updates the ai-worker go dependency to version v0.12.1.
This commit ensures that the I2V temporary files created during transcoding are removed after the object storage is successfully created by the orchestrator.
This commit ensures that the VERSION file is updated so that the version capability constraint works.
This PR introduces the AI features into go-livepeer.
Original comment from Yodon