2.3k citations · 2.6k across the 21 of their papers we have counts for
21 papers
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +572
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA, :, Aaron Blakeman +356
We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a…
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +311
We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 t…
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
NVIDIA, :, Aarti Basant +214
We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compar…
PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries
Steven Kolawole, Keshav Santhanam, Virginia Smith +1
LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contai…
ColBERT-serve: Efficient Multi-Stage Memory-Mapped Scoring
Kaili Huang, Thejas Venkatesh, Uma Dingankar +9
We study serving retrieval models, specifically late interaction models like ColBERT, to many concurrent users at once and under a small budget, in which the index may not fit in m…
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
NVIDIA, :, Aaron Blakeman +198
As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemo…
Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry
Deepti Raghavan, Keshav Santhanam, Muhammad Shahir Rahman +7
Compound AI applications chain together subcomponents such as generative language models, document retrievers, and embedding models. Applying traditional systems optimizations such…
When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
Norah Alzahrani, Hisham Abdullah Alyahya, Yazeed Alnumay +9
Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are take…
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Omar Khattab, Arnav Singhvi, Paridhi Maheshwari +10
The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipel…
Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs
Deepak Narayanan, Keshav Santhanam, Peter Henderson +3
Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference ti…
UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers
Jon Saad-Falcon, Omar Khattab, Keshav Santhanam +6
Many information retrieval tasks require large labeled datasets for fine-tuning. However, such datasets are often unavailable, and their utility for real-world applications can dim…
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Omar Khattab, Keshav Santhanam, Xiang Lisa Li +4
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Exi…
Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking
Keshav Santhanam, Jon Saad-Falcon, Martin Franz +7
Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some di…
Holistic Evaluation of Language Models
Percy Liang, Rishi Bommasani, Tony Lee +47
Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Hol…
Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding
William Chen, Siyi Hu, Rajat Talak +1
Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of a…
PLAID: An Efficient Engine for Late Interaction Retrieval
Keshav Santhanam, Omar Khattab, Christopher Potts +1
Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and rece…
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
Keshav Santhanam, Omar Khattab, Jon Saad-Falcon +2
Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-ve…
DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution
Keshav Santhanam, Siddharth Krishna, Ryota Tomioka +2
The rapidly growing size of deep neural network (DNN) models and datasets has given rise to a variety of distribution strategies such as data, tensor-model, pipeline parallelism, a…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads
Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka +2
Specialized accelerators such as GPUs, TPUs, FPGAs, and custom ASICs have been increasingly deployed to train deep learning models. These accelerators exhibit heterogeneous perform…