iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
US Stock Markets Rally as Chip Stock Gains Lift Nasdaq, S&P 500 and Dow SEBI Clarifies Unlisted Share Sale Rules: 200-Buyer Private Deal Limit GeM completes 10 years as India's trusted digital public procurement platform Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Bloomberg Delays India's Sovereign Bond Index Inclusion as Market Reforms Need Further Testing US Stock Markets Rally as Chip Stock Gains Lift Nasdaq, S&P 500 and Dow SEBI Clarifies Unlisted Share Sale Rules: 200-Buyer Private Deal Limit GeM completes 10 years as India's trusted digital public procurement platform Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Bloomberg Delays India's Sovereign Bond Index Inclusion as Market Reforms Need Further Testing
Home ›› Technology ›› Ai ›› Llms ›› UltraQuant: 4-bit KV Caching Achieves 3.47x Latency Cut for Context-Heavy AI Agents

UltraQuant: 4-bit KV Caching Achieves 3.47x Latency Cut for Context-Heavy AI Agents

A new technique called UltraQuant compresses the key-value cache in large language models to 4 bits, achieving a 3.47x reduction in latency and 1.63x increase in throughput for context-heavy, multi-turn agent workloads on AMD GPUs. The method, detailed in an arXiv paper, adapts rotation and codebook quantization for robust long-context serving.

iG
iGEN Editorial
June 20, 2026
UltraQuant: 4-bit KV Caching Achieves 3.47x Latency Cut for Context-Heavy AI Agents

Enterprise AI agents that maintain long conversational contexts — such as supply chain chatbots handling multi-step logistics queries or customer support bots with extensive session histories — face a persistent bottleneck: the key-value (KV) cache. As context length grows, this cache consumes GPU memory and increases latency. A new pre-print from researchers at AMD and other institutions introduces UltraQuant, a 4-bit KV-cache compression method that promises to cut time-to-first-token by 3.47x in cache-pressured late rounds and improve output throughput by 1.63x over the standard FP8 baseline.

The Problem with Context-Heavy Agents

Context-heavy agents reuse long prefixes across many short turns, a pattern that strains serving infrastructure. According to the arXiv paper by Chakrabarti et al., concurrent users amplify pressure on the KV cache, determining whether GPUs stay utilized. Existing FP8 KV caching (as in vLLM) provides a baseline, but the authors argue that joint measurement of task quality, cache residency, and serving throughput is needed for agent workloads. Traditional 4-bit compression often degrades quality; UltraQuant aims to make it robust.

UltraQuant's Approach

The researchers frame 4-bit KV caching around multi-turn agent workloads. They describe practical design choices to make the 4-bit path robust:

  • Asymmetric K/V treatment: separate quantization strategies for keys and values to preserve quality.
  • Walsh-Hadamard rotation: a fast transform that distributes outlier values across dimensions, improving quantization fidelity.
  • QJL removal: skipping Query-Johnson-Lindenstrauss projections to simplify the pipeline.
  • Block-scale variants: grouping tokens into blocks with shared scaling factors for finer granularity.

The UltraQuant path specifically uses an FP4 approximation: FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA support on AMD's CDNA4 architecture. This combination enables efficient execution on AMD GPUs.

Results on AMD GPUs

On a long-context, multi-turn agentic workload, UltraQuant demonstrated significant performance gains over the FP8 KV baseline:

Metric Improvement vs FP8 Baseline
P50 time-to-first-token (late rounds, cache-pressured) 3.47x faster
P50 time-to-first-token (all rounds) 2.3x faster
Output throughput 1.63x higher

These results highlight the method's effectiveness under the exact conditions where context-heavy agents suffer most: long prefixes, many short turns, and high concurrency.

Implications for Enterprise AI

For enterprise customers deploying AI agents — whether for trade document analysis, customs classification, or logistics visibility — every millisecond of latency directly impacts user experience and throughput. UltraQuant's 4-bit compression allows more agent instances per GPU, lowering total cost of ownership. The technique is particularly relevant for companies building on AMD infrastructure, where native FP4 and scaled-MFMA support on CDNA4 can be leveraged without custom kernel development.

The paper's emphasis on robustness — through asymmetric K/V processing and block-scale variants — addresses a common barrier to adopting low-bit quantization in production. TurboQuant-style rotation serves as a quality anchor, while vLLM FP8 caching provides the deployment benchmark. As LLM-powered agents become standard in trade finance, supply chain coordination, and customs automation, efficient caching techniques like UltraQuant will be critical to scaling these systems cost-effectively.

The research is led by Chakrabarti, Inesh, Limpus, David, Rana, Aditi Ghai, Bao, Bowen, Tiwari, Spandan, Crepaldi, Thiago, and Sirasao, Ashish. The full paper is available on arXiv.


Sources:

Keep Reading

Recommended Stories

Can In-Context Learning Enable Efficient Data Exploration for Enterprise AI? Technology

Can In-Context Learning Enable Efficient Data Exploration for Enterprise AI?

A research paper investigates whether in-context learning (ICL) can enable intrinsic curiosity—automated data selection—without costly gradient updates. The authors prove that in general Markov decision processes, ICL-based rewards cannot unbiasedly estimate learning progress, but in non-temporal settings like active learning, they succeed. Controlled experiments validate the theory.

July 8, 2026
LLM Paraphrase Augmentation Boosts Sign Language Translation Performance Technology

LLM Paraphrase Augmentation Boosts Sign Language Translation Performance

A new study proposes using a large language model (GPT-4o) to generate controlled paraphrase variants of training targets for sign language translation (SLT). Evaluated on three datasets, the method yields a modest BLEU-4 improvement on PHOENIX14T and reveals gains in semantic fidelity not captured by lexical metrics.

June 21, 2026
Reinforcement-Aware Knowledge Distillation Boosts LLM Reasoning Efficiency Technology

Reinforcement-Aware Knowledge Distillation Boosts LLM Reasoning Efficiency

Researchers propose RL-aware distillation (RLAD) to address distribution mismatch and objective interference in knowledge distillation for LLM reasoning. The method uses Trust Region Ratio Distillation (TRRD) to selectively imitate teacher policies during reinforcement learning. RLAD outperforms offline distillation, standard GRPO, and KL-based on-policy distillation across logic and math benchmarks.

June 21, 2026
Simulating Language Evolution Under Regulated Social Media Using LLMs and Genetic Algorithms Technology

Simulating Language Evolution Under Regulated Social Media Using LLMs and Genetic Algorithms

A new research paper presents a multi-agent framework using Large Language Models and genetic algorithms to simulate how language strategies evolve under regulated social media platforms. The framework, tested on a password game and an illegal pet trade scenario, shows significant improvement in uninterrupted dialogue turns and information transmission accuracy over increasing rounds. A user study with 40 participants validated the realism.

June 21, 2026