llm-routing
SPROUTSPROUT-o3minidaily-paper-2026-08-08-precision-tier-llm-routing
Precision-Tier Routing: Per-Request Quantization-Level Selection for Cost-Optimal LLM Serving on H200
TL;DR — Precision-tier routing: a lightweight classifier routes each LLM request to BF16, W4A16, or NVFP4 variants of the same checkpoint, recovering near-BF16 accuracy at NVFP4 cost by serving easy requests cheaply and reserving expensive precision for hard ones.
ThakiCloud AI Research · 2026-08-08 · 📝 Tech blog (KO)
Problem
LLM serving fleets pick one… See the full description on the dataset page: https://huggingface.co/datasets/thaki-AI/daily-paper-2026-08-08-precision-tier-llm-routing.modality-routing-dataset
Modality Routing Dataset
This dataset materializes the dynamic modality routing data builder used by the local
mmBERT-32K modality router training pipeline. The export is intended for review,
versioning, and uploading to a Hugging Face dataset repository.
Labels
Label
ID
Description
AR
0
Text-only requests that should route to an autoregressive LLM.
DIFFUSION
1
Image-generation requests that should route to a diffusion model.
BOTH
2
Requests that benefit… See the full description on the dataset page: https://huggingface.co/datasets/llm-semantic-router/modality-routing-dataset.llm-routing-response-bank
LLM Routing Response Bank
Five language models × 13,315 tasks across four benchmark families, with
per-response text, binary quality scores, token usage, and official billing.
Collected for a routing study with a paired calibration/evaluation design:
256 calibration tasks, 13,059 evaluation tasks.
Contents
file
rows
note
tasks_cal.jsonl / tasks_eval.jsonl
256 / 13,059
prompts + reference answers; gpqa_diamond rows are hash-only (see below)… See the full description on the dataset page: https://huggingface.co/datasets/Lurume/llm-routing-response-bank.llm-routing-text-classification
Prompt Task Clasification
Category prompt into categories and results into the most probably task
Current Supported Categories
['fill_mask',
'conversation',
'midjourney_image_generation',
'math',
'science',
'toxic_harmful',
'logical_reasoning',
'sex',
'creative_writing']
Categories Data Composition
![Categories Composition](data:image/png;base64… See the full description on the dataset page: https://huggingface.co/datasets/jeanvydes/llm-routing-text-classification.