llm-serving
llm-serving-selector-regret
LLM-Serving Selector Regret
LLM-Serving Selector Regret is a metrics-only research dataset for studying learned policy selection in LLM-serving schedulers. It contains derived selector/oracle/regret objects generated by Soroush Vahidi's research workflow, not raw request traces.
Creator / Provider
Dataset creator/provider: Soroush Vahidi.
The released selector/regret and policy-suitability metrics were generated by Soroush Vahidi's research workflow. Underlying… See the full description on the dataset page: https://huggingface.co/datasets/SoroushVahidi/llm-serving-selector-regret.llm-serving-scheduler-portability
LLM-Serving Scheduler Portability (LSSP) — v1.0.0
LSSP measures how portable comparative LLM-serving scheduler rankings
are across workload sources, load regions, evaluation metrics, and SLO
definitions: does the best-performing scheduling policy stay best when
you change the traffic source or the load level, or do rankings reverse?
This dataset is the derived analysis behind that question, paired with a
selected-case physical validation (RQ6).
The underlying simulator campaign… See the full description on the dataset page: https://huggingface.co/datasets/SoroushVahidi/llm-serving-scheduler-portability.llm-serving-scheduler-baselines
LLM-Serving Scheduler Baselines: Simulation Performance Outcomes for Scheduler Policies
This is a comprehensive, text-free, highly structured simulation results dataset for large language model (LLM) serving schedulers. It contains policy-level outcome records generated across synthetic scheduler stress tests and an added TraceLab-derived out-of-distribution policy sweep. The dataset compares 12 highly optimized third-party baseline schedulers against APT-Serve (a… See the full description on the dataset page: https://huggingface.co/datasets/SoroushVahidi/llm-serving-scheduler-baselines.serving-llm-tgi
Dataset Card for serving-llm-tgi
This dataset has been created with distilabel.
Dataset Summary
This dataset contains a pipeline.yaml which can be used to reproduce the pipeline that generated it in distilabel using the distilabel CLI:
distilabel pipeline run --config "https://huggingface.co/datasets/distilabel-internal-testing/serving-llm-tgi/raw/main/pipeline.yaml"
or explore the configuration:
distilabel pipeline info --config… See the full description on the dataset page: https://huggingface.co/datasets/distilabel-internal-testing/serving-llm-tgi.