LLM with Streaming
Building an LLM with streaming output
View on Github
In this example, we go through a Truss that serves the Qwen 7B Chat LLM, and streams the output to the client.
Why Streaming?
For certain ML models, generations can take a long time. Especially with LLMs, a long output could take 10-20 seconds to generate. However, because LLMs generate tokens in sequence, useful output can be made available to users sooner. To support this, in Truss, we support streaming output.
Set up the imports
In this example, we use the HuggingFace transformers library to build a text generation model.
Define the load function
In the load
function of the Truss, we implement logic
involved in downloading the chat version of the Qwen 7B model and loading it into memory.
Define the preprocess function
In the preprocess
function of the Truss, we set up a generate_args
dictionary with some generation arguments from the inference request to be used in the predict
function.
Define the predict function
In the predict
function of the Truss, we implement the actual
inference logic.
The two main steps are:
- Tokenize the input
- Call the model’s
generate
function if we’re not streaming the output, otherwise call thestream
helper function
Define the stream
helper function
In this helper function, we’ll instantiate the TextIteratorStreamer
object, which we’ll later use for
returning the LLM output to users.
When creating the generation parameters, ensure to pass the streamer
object
that we created previously.
Spawn a thread to run the generation, so that it does not block the main thread.
In Truss, the way to achieve streaming output is to return a generator
that yields content. In this example, we yield the output of the streamer
,
which produces output and yields it until the generation is complete.
We define this inner
function to create our generator.
Setting up the config.yaml
Running Qwen 7B requires torch, transformers, and a few other related libraries.
Configure resources for Qwen
Note that we need an A10G to run this model.
Deploy Qwen 7B Chat
Deploy the model like you would other Trusses, with:
Was this page helpful?