[Feature]: Add TurboQuant Support for KV Cache Quantization
# [Feature]: Add TurboQuant Support for KV Cache Quantization ## 🚀 The feature, motivation and pitch **TurboQuant** is a novel online vector quantization method that achieves near-optimal distortion rates for both MSE and inner product preservation, specifically designed for KV cache compression in LLMs. As described in the paper [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://arxiv.org/pdf/2504.19874), this method provides: - **Provably optimal distortion bounds** within a factor of ~2.7 of information-theoretic limits - **Unbiased inner product estimation** - critical for attention mechanisms - **Online application** - no data-dependent preprocessing required - **Accelerator-friendly design** - suitable for real-time AI workloads - **Significant memory savings** - 4-5× compression while maintaining model performance The paper demonstrates TurboQuant achieving perfect recall on Needle-in-a-Haystack tests at 4× compression and competitive performance on LongBench with just 2.5-3.5 bits per dimension. This would be a valuable addition to vLLM's quantization portfolio, complementing existing scalar methods (FP8, INT4, etc.) with a vector quantization approach specifically optimized for attention KV caches. ## Alternatives Current vLLM KV cache quantization options include: - **FP8 quantization** (`fp8_e4m3`, `fp8_e5m2`) - scalar quantization with element-wise MSE optimization - **Compressed-tensors KV cache** - supports various schemes but primarily scalar-based - **ModelOpt FP8** - NVIDIA's FP8 implementation TurboQuant differs by: 1. Using **vector quantization** with learned codebooks instead of scalar quantization 2. Optimizing for **inner product preservation** rather than just MSE 3. Providing **theoretical guarantees** on distortion bounds 4. Supporting **variable bit-widths** (2.5-bit, 3.5-bit) through outlier handling ## Additional context ### Technical Integration Approach Based on vLLM's existing quantization f
FL score
out of 100
Verdict
high confidence
Competition
No competitor data yet
Trend
No signal yet
Add TurboQuant vector quantization support to LLM KV caches to reduce memory use while preserving attention accuracy.
The pain
The gap
Build angle
Strengths
- Strong theoretical foundation with provable distortion bounds
- Novel vector quantization approach optimized for attention mechanisms
- Compatible with existing LLM serving frameworks like vLLM
- Potential for significant memory savings (4-5x compression)
Risks
- Narrow target market limited to AI infrastructure and LLM serving providers
- Requires specialized expertise to implement and maintain
- Adoption depends on demonstrated real-world performance gains
- Potential integration complexity with diverse hardware accelerators
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 85
- Solution gap
- 80
- Willingness to pay
- 80
- Buildability
- 85
The idea addresses a clear technical pain in LLM KV cache compression with a novel vector quantization method that fills a gap beyond scalar quantization, has a plausible paying user base in AI infrastructure, and is feasible to build given existing vLLM integration.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
The feature targets a specific, measurable pain in memory and performance tradeoffs for LLM KV caches, offers a differentiated solution with theoretical guarantees, and fits a market with growing demand for efficient LLM serving.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
The idea leverages a strong technical foundation and addresses a niche but important problem in LLM quantization, though the market size and direct monetization path are somewhat limited to specialized AI infrastructure users.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
The feature is well aligned with a real technical bottleneck, offers a unique approach with provable benefits, and can be integrated into existing tools, but requires specialized expertise and adoption by a technical user base.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
The idea solves a concrete problem for LLM performance optimization with a novel method that improves on existing quantization techniques, but the customer base is narrow and the business model depends on adoption by AI infrastructure providers.
Five lenses, one composite. How scoring works
The angle
No market research recorded for this idea yet.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “[Feature]: Add TurboQuant Support for KV Cache Quantization”.