Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extension on a single H200 | by RightNow https://www.rightnowai.co/
☆27May 5, 2026Updated 5 months ago
Alternatives and similar repositories for StreamIndex
Users that are interested in StreamIndex are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆27Jul 22, 2026Updated 3 months ago
- GEMMs with metal☆26Oct 5, 2026Updated 2 weeks ago
- the agi compiler: records llm agent behavior, proves what repeats, and compiles it into verified, sandboxed wasm binaries that run for mi…☆129Jul 7, 2026Updated 3 months ago
- ☆28Mar 31, 2026Updated 6 months ago
- FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.☆112Jul 18, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆49Aug 27, 2026Updated last month
- ☆44Jul 23, 2026Updated 3 months ago
- Phoenix is a direct hub between storage and xPU — plug in any accelerator (GPU/NPU) or AI app and stream data straight to the chip.☆28Updated this week
- DeepTrace: A lightweight, scalable real-time diagnostic and analysis tool for distributed training tasks.☆18Nov 4, 2025Updated 11 months ago
- fused MoE kernel in Candle backend☆14Feb 3, 2026Updated 8 months ago
- ☆27Jul 13, 2026Updated 3 months ago
- Multi-Word Probabilistic based supertokenizer☆15May 15, 2025Updated last year
- Build a compiler to solve Anthropic's interview challenge.☆135Jul 12, 2026Updated 3 months ago
- ☆23Dec 7, 2023Updated 2 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Graph model execution API for Candle☆19Jul 27, 2025Updated last year
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse☆146Mar 14, 2026Updated 7 months ago
- An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch…☆154Sep 18, 2026Updated last month
- LLM inference optimization simulator☆13Jul 12, 2025Updated last year
- 基于 CUDA Driver API 的 cuda 运行时环境☆16Jul 30, 2025Updated last year
- Repository for the listwise reranker Rank-K☆16May 23, 2025Updated last year
- ☆21Jul 23, 2026Updated 3 months ago
- [ECCV 2024] Official Implementation of CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings☆10Feb 24, 2025Updated last year
- HUD for CI activity on `pytorch/pytorch`, provides a top level view for jobs to easily discern regressions☆13Feb 26, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A Scheduler for Batched LLM Inference☆19Oct 5, 2025Updated last year
- Serve DeepSeek V4 Flash + DSpark on 4x RTX PRO 6000 (AWS g7e.24xlarge)☆27Aug 11, 2026Updated 2 months ago
- Simple intermediate representation language for learning and research.☆22Mar 27, 2020Updated 6 years ago
- tensorrt部署教程☆11Aug 1, 2025Updated last year
- ☆75Oct 31, 2024Updated last year
- ☆75Nov 22, 2024Updated last year
- A PCIe RTL implementation☆26Aug 16, 2026Updated 2 months ago
- The github repository of ChatLM.☆11Mar 16, 2024Updated 2 years ago
- ☆12Feb 18, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Dynamic weight generation for recursive transformers via input-conditioned LoRA modulation☆36Apr 2, 2026Updated 6 months ago
- watchOS kernel R/W + live process memory dumping on Apple Watch Series 4 (watchOS 10.6.2 - latest). Named after the children's book Peepo…☆30Jun 22, 2026Updated 4 months ago
- Sparse Decoupled Attention for Efficient Long-Context LLM Inference☆74Jun 4, 2026Updated 4 months ago
- ☆24Jun 5, 2025Updated last year
- A high performance batching router optimises max throughput for text inference workload☆16Sep 6, 2023Updated 3 years ago
- A curated list of awesome papers about utilizing large language models for ranking.☆33Apr 12, 2026Updated 6 months ago
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Oct 7, 2026Updated 2 weeks ago