diff --git a/README.md b/README.md index cf6a30dbf82..cc9d523f0ae 100644 --- a/README.md +++ b/README.md @@ -189,7 +189,7 @@ overridden with the `--otlp-service-name` argument ![TGI architecture](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/TGI.png) -Detailed blogpost by Adyen on TGI inner workings: [LLM inference at scale with TGI](https://www.adyen.com/knowledge-hub/llm-inference-at-scale-with-tgi) +Detailed blogpost by Adyen on TGI inner workings: [LLM inference at scale with TGI (Martin Iglesias Goyanes - Adyen, 2024)](https://www.adyen.com/knowledge-hub/llm-inference-at-scale-with-tgi) ### Local install diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml index f52fa2ec2a5..b883b36d6c8 100644 --- a/docs/source/_toctree.yml +++ b/docs/source/_toctree.yml @@ -71,6 +71,8 @@ title: How Guidance Works (via outlines) - local: conceptual/lora title: LoRA (Low-Rank Adaptation) + - local: conceptual/external + title: External Resources title: Conceptual Guides diff --git a/docs/source/conceptual/external.md b/docs/source/conceptual/external.md new file mode 100644 index 00000000000..9cbe1b5aee9 --- /dev/null +++ b/docs/source/conceptual/external.md @@ -0,0 +1,4 @@ +# External Resources + +- Adyen wrote a detailed article about the interplay between TGI's main components: router and server. +[LLM inference at scale with TGI (Martin Iglesias Goyanes - Adyen, 2024)](https://www.adyen.com/knowledge-hub/llm-inference-at-scale-with-tgi) diff --git a/docs/source/conceptual/streaming.md b/docs/source/conceptual/streaming.md index f1f37f2a980..b8154ba4355 100644 --- a/docs/source/conceptual/streaming.md +++ b/docs/source/conceptual/streaming.md @@ -155,7 +155,3 @@ SSEs are different than: * Webhooks: where there is a bi-directional connection. The server can send information to the client, but the client can also send data to the server after the first request. Webhooks are more complex to operate as they don’t only use HTTP. If there are too many requests at the same time, TGI returns an HTTP Error with an `overloaded` error type (`huggingface_hub` returns `OverloadedError`). This allows the client to manage the overloaded server (e.g., it could display a busy error to the user or retry with a new request). To configure the maximum number of concurrent requests, you can specify `--max_concurrent_requests`, allowing clients to handle backpressure. - -## External sources - -Adyen wrote a nice recap of how TGI streaming feature works. [LLM inference at scale with TGI](https://www.adyen.com/knowledge-hub/llm-inference-at-scale-with-tgi)