add BEI doc #405
Merged
add BEI doc #405
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
philipkiely-baseten
approved these changes
Feb 11, 2025
| This is a collection of BEI deployments with Baseten. BEI is Baseten's solution for production-grade deployments via TensorRT-LLM. | ||
|
|
||
| With BEI you get the following benefits: | ||
| - *lowest-latency inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama)*1 |
There was a problem hiding this comment.
Suggested change
| - *lowest-latency inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama)*1 | |
| - *Lowest-latency inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama)<sup>1</sup> |
|
|
||
| With BEI you get the following benefits: | ||
| - *lowest-latency inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama)*1 | ||
| - *highest-throughput inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama) - thanks to XQA kernels, FP8 and dynamic batching.*2 |
There was a problem hiding this comment.
Suggested change
| - *highest-throughput inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama) - thanks to XQA kernels, FP8 and dynamic batching.*2 | |
| - *Highest-throughput inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama) - thanks to XQA kernels, FP8 and dynamic batching.<sup>2</sup> |
| With BEI you get the following benefits: | ||
| - *lowest-latency inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama)*1 | ||
| - *highest-throughput inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama) - thanks to XQA kernels, FP8 and dynamic batching.*2 | ||
| - high parallelism: up to 1400 client embeddings per second |
There was a problem hiding this comment.
Suggested change
| - high parallelism: up to 1400 client embeddings per second | |
| - High parallelism: up to 1400 client embeddings per second |
| - *lowest-latency inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama)*1 | ||
| - *highest-throughput inference* across any embedding solution (vLLM, SGlang, Infinity, TEI, Ollama) - thanks to XQA kernels, FP8 and dynamic batching.*2 | ||
| - high parallelism: up to 1400 client embeddings per second | ||
| - cached model weights for fast vertical scaling and high availability - no Hugging Face hub dependency at runtime |
There was a problem hiding this comment.
Suggested change
| - cached model weights for fast vertical scaling and high availability - no Hugging Face hub dependency at runtime | |
| - Cached model weights for fast vertical scaling and high availability - no Hugging Face hub dependency at runtime |
11-embeddings-reranker-classification-tensorrt/BEI-baai-bge-en-icl-embedding/README.md
Outdated
Show resolved
Hide resolved
11-embeddings-reranker-classification-tensorrt/BEI-baai-bge-en-icl-embedding/README.md
Outdated
Show resolved
Hide resolved
| } | ||
| ``` | ||
| Advanced: | ||
| You may also use Baseten's async jobs API, which returns a request_id, which you can use to query the status of the job and get the results. |
There was a problem hiding this comment.
Suggested change
| You may also use Baseten's async jobs API, which returns a request_id, which you can use to query the status of the job and get the results. | |
| You may also use Baseten's async jobs API, which returns a request_id, which you can use to query the status of the job and get the results.\n |
11-embeddings-reranker-classification-tensorrt/BEI-baai-bge-en-icl-embedding/README.md
Outdated
Show resolved
Hide resolved
11-embeddings-reranker-classification-tensorrt/BEI-baai-bge-en-icl-embedding/README.md
Outdated
Show resolved
Hide resolved
|
All suggestions applied! |
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.
they are AUTOGENERATED! please look at generate.py.