[Bug]: RankLLMRerank cannot be imported without vllm installed, regardless of reranking backend
RankLLMRerank cannot be imported, unless vllm is installed. This is true even when using a backend that has nothing to do with vLLM. Reason: llama_index.postprocessor.rankllm_rerank.base imports PromptMode and Reranker from rank_llm.rerank at module level: In the current release 0.25.7, importing anything from rank_ll…
run-llama/llama_index
Eligibility
Check before you begin
For students with basic Git skills who can follow the repository contribution guide; confirm with maintainers before starting.
What you will practice
Related skills
The source does not list specific skills yet. Read the original page before deciding.
Source and verification
Where this information comes from
Keep exploring
Items in the same direction
[Feature]: Tracking Whisper feature requests
This issue is for keeping track of the recurrent Whisper asks as well as the linked on-going efforts to support that feature, if any. When a feature request has no linked PR, feel free to claim the work here if you want to help! - Related issues: https://github.com/vllm-project/vllm/issues/19556, https://github.com/vl…
foreach_map enhancements
These enhancements are to have a better UX when using foreach_map, suggested in a few places, but most recently, https://github.com/pytorch/pytorch/issues/158371#issuecomment-3088757068 These enhancements should allow easier compiler-first custom optimizer implementations. cc @chauhang @penguinwu @voznesenskym @EikanW…
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
The Shift to Tabular Foundation Models Tabular data is the backbone of enterprise machine learning. Customer records, transactions, sensor logs, claims, and orders all live in tables, and predicting churn, default, demand, or price from them is among the most common machine learning tasks in industry. For two decades,…
tokenizers v1: encode, decode and scaling, measured
As models become faster and workloads scale, that balance begins to shift. Training on massive datasets, serving many concurrent requests, or repeatedly processing long inputs can put enough pressure on the tokenizer that it starves the model of data.