Alternatives
Products that do what Parmar does
AI pre-filter optimizing LZMA data compression.
- 1
- 2
- 314
2021 · gist.github.com
- 4TA
2015 · ruarai.github.io
- 5
- 6
- 7
- 8TB
2015 · github.com
- 9DR
2018 · dropbox.github.io
- 10OS
I’ve been working on a compression algorithm for fast random access to individual strings in large collections. The problem came up when working with large in-memory database columns (emails, URLs, product titles, etc.), where low-latency point queries are essential. With short strings, LZ77-based compressors don’t perform well. Block compression helps, but block size forces a trade-off between ratio and access speed. Some existing options: - BPE: good ratios, but slow and memory-heavy - FSST (discussed here: https://news.ycombinator.com/item?id=41489047): very fast, but…
2025 · github.com
- 11TE
2021 · github.com
- 12XC
2019 · github.com
- 13RB
Sep 2025 · github.com
- 14MM
Hi HN! We (Thomas and Stéphan, hello!) recently released Model2Vec, a Python library for distilling any sentence transformer into a small set of static embeddings. This makes inference with such a model up to 500x faster, and reduces model size by a factor of 15 (7.5M params or 15/30MB on disk, depending on whether you use float16 or float32). This allows you to embed 50-100k documents per second on a cpu on a macbook. This reduction of course comes at a cost: distilled models are worse than their parent models. Even so, they are actually a lot better than large sets of conventional…
2024 · github.com
- 15PA
Hello Hacker News! I am Bertrand from Pruna AI. With my associates, John, Rayan, and Stephan, we are fellow researchers in AI efficiency and reliability coming from TUM. We are building an optimization engine that combines compression methods (e.g. quantization, pruning, compilation, batching…) in the aim of saving compute power when running AI models. This optimization engine take one base model as input and returns a compressed model as output. It aims to help for two things: - Make various AI models faster and/or smaller for various hardware (because they can require significant…
2024
- 16AO
Hi, We are building an open-source framework for loading and structuring LLM context to create accurate and explainable LLM answers using knowledge graphs and vector stores. We built the tool with four main concepts in mind: 1. Loader -> uses dlt in the backend to load and structure the data 2. Cognify step -> creates a graph with summaries, labels and factoids that are interconnected across the documents and stored as a representation in the vector store 3. Optimizer -> Uses DSPy to optimize LLM queries, and we plan to extend it to most of the knobs we can turn, like chunking etc. 4. Search…
2024 · github.com
- 17IM
Every time I wanted to use LLMs in my existing pipelines the integration was very bloated, complex, and too slow. This is why I created a lightweight library that works just like scikit-learn, the flow generally follows a pipeline-like structure where you “fit” (learn) a skill from sample data or an instruction set, then “predict” (apply the skill) to new data, returning structured results. High-Level Concept Flow Your Data --> Load Skill / Learn Skill --> Create Tasks --> Run Tasks --> Structured Results --> Downstream Steps And the bast part: Every step can be saved and reused as…
2025 · github.com
- 18IM
Jan 2026 · github.com
- 19WB
Here is a production-first Keras-inspired LM framework, built with the advice of François Chollet (ex-Google, creator of Keras and ARC-AGI), our technical advisor. This system have already been deployed in production with our clients (which is why we have already every LLMOps practice implemented). It is also compatible with Jupyter and Marimo to integrate seamlessly in you Data Scientists workflows. You can try the code examples online on HF space and you can find more information in the documentation and FAQ. If you have any feedback for us don't hesitate to join our discord! More releases…
2025 · github.com
- 20AD
We just launched Turbine, it automates the data pipeline for LLM powered apps. It fetches data from your database, creates embeddings from the data, and stores in a vector database for easy semantic search. It also creates a real-time data pipeline to fetch changes and keep the search data fresh. Turbine supports multiple source databases, embedding models and vector databases. It's aimed to be configurable and easy to use at the same time. It's primary use case would be being the data backend for LLM apps—to create a relevant context for each prompt from your data. We are very early and…
2023 · useturbine.com
- 21BA
I built CodeLens.AI - a tool that compares how 6 top LLMs (GPT-5, Claude Opus 4.1, Claude Sonnet 4.5, Grok 4, Gemini 2.5 Pro, o3) handle your actual code tasks. How it works: - Upload code + describe task (refactoring, security review, architecture, etc.) - All 6 models run in parallel (~2-5 min) - See side-by-side comparison with AI judge scores - Community votes on winners (blind voting) - Each evaluation gets reflected in the overall AI model leaderboard, showing us best ones Why I built this: Existing benchmarks (HumanEval, SWE-Bench) don't reflect real-world developer tasks. I wanted to…
Oct 2025 · codelens.ai
- 22IB
I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things. The stack is Phoenix/Oban on the orchestrator side, and Python/FastAPI/Instructor for the AI workers. Happy to answer any questions about the architecture,…
Apr 2026 · qwelian.com
- 23AN
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026
- 24SL
I'd like to share a little toy project of mine, a really simple image codec that can do lossy to full lossless image compression with complete scalability at a byte level granularity - you can compress an image just once, even fully losslessly if needed, and then get any lossy version possible by simply stopping decompression at any offset in the compressed data. This "encode onde, serve many" approach is especially interesting for providing downscaled low quality image previews (LQIP) in as tight a storage budget as possible, and then allowing seamless, transparent refinement as deemed…
2024 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →