Function server #1641
Merged
Function server #1641
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
pseudotensor
force-pushed
the
function_server
branch
3 times, most recently
from
cda8709
to
8a76cbf
Compare
pseudotensor
force-pushed
the
function_server
branch
from
8a76cbf
to
96fb03f
Compare
…se in some extreme limits
pseudotensor
force-pushed
the
function_server
branch
from
3086d5c
to
65eec19
Compare
|
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Parallel and Isolated OpenAI Proxy Servers
will launch 2 OpenAI proxy servers using FastAPIs workers, so each is a separate fork independent of any other process.
This speeds up any calls to the OpenAI server, letting FastAPI handle concurrency and load balancing between the different workers using same IP/port via OS management.
Parallel and Isolated Ingestion Servers
will launch 2 Ingestion proxy servers using FastAPIs workers, so each is a separate fork independent of any other process. If ASR, DocTR, captions, etc. are enabled, these will be run on same GPUs in separate processes.
This helps keep the main UI server isolated from ingestion tasks that can consume alot of cpu or hang the Gradio server.