aiqbench takeAI Products
aiqbench analysis
LiteLLM is a library for calling many LLM providers through one interface, and this release slims its default install by splitting out a core package. It drops mandatory AWS and Hugging Face tokenizer dependencies and the bundled dashboard, saving about 65.6 MB in the authors' source-build comparison. Developers who only need chat completions, streaming, embeddings, or cost tracking will see lighter installs, while routing, retries, and fallbacks stay in core and optional features still require their packages.
1
Source coveringLiteLLM Blog
Introducing litellm-core: the first step toward a leaner SDK
LiteLLM Blog4 min read
Ongoing work to reduce LiteLLM's dependencies and installation footprint, improve runtime loading, and make imports faster
We're introducing litellm-core as the first step in ongoing work to make the LiteLLM SDK leaner. We want applications to install fewer dependencies, use less disk space, and spend less time loading the SDK This first step delivers an approximately 65.6 MB reduction in installed disk space, including runtime dependencies, compared with baseline litellm in our source-build comparison. We'll continue building on that progress with further dependency reductions and improvements to how the SDK…
Excerpt shown under the publisher's RSS terms · 74 words · full text and figures are on the publisher's site