Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"
☆29Apr 17, 2026Updated 2 months ago
Alternatives and similar repositories for saw-int4
Users that are interested in saw-int4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆71Apr 30, 2026Updated 2 months ago
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆17May 20, 2026Updated last month
- ☆28Jun 1, 2026Updated last month
- Lightweight harness for replaying inference traffic against an endpoint☆21Jul 2, 2026Updated last week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆73Oct 2, 2025Updated 9 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆16May 27, 2026Updated last month
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆95Updated this week
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆56Aug 6, 2025Updated 11 months ago
- Checkpointable dataset utilities for foundation model training☆32Jan 29, 2024Updated 2 years ago
- The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generat…☆22Updated this week
- the xoroshiro32++ and xoroshiro64++ PRNG algorthims by David Blackman and Sebastiano Vigna in C++, Verilog, VHDL and SpinalHDL.☆16Dec 2, 2018Updated 7 years ago
- ☆83Jun 20, 2025Updated last year
- [ICML2026] Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization☆60Jun 4, 2026Updated last month
- A PYNQ overlay demonstrating the Xilinx RFSoC SD-FEC☆13Jun 29, 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.
- VidKV: Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models☆26Mar 26, 2025Updated last year
- build and benchmark deep research☆244Mar 28, 2026Updated 3 months ago
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆33May 26, 2026Updated last month
- The tool facilitates debugging convergence issues and testing new algorithms and recipes for training LLMs using Nvidia libraries such as…☆21Sep 17, 2025Updated 9 months ago
- Framework based on Partial Reconfiguration for chip characterization utilizing ring-oscillator PUFs☆14Apr 1, 2020Updated 6 years ago
- NPUEval is an LLM evaluation dataset written specifically to target AIE kernel code generation on RyzenAI hardware.☆32Nov 8, 2025Updated 8 months ago
- Official repository Flash Local Linear Attention☆37May 28, 2026Updated last month
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆32Apr 14, 2026Updated 3 months ago
- Program to scan for malicious FPGA designs.☆17Mar 20, 2021Updated 5 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.
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆21Jan 24, 2025Updated last year
- A fork of llama3.c used to do some R&D on inferencing☆23Dec 20, 2024Updated last year
- MLPruning, PyTorch, NLP, BERT, Structured Pruning☆20Jun 29, 2021Updated 5 years ago
- ☆13Mar 5, 2025Updated last year
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆34Feb 17, 2024Updated 2 years ago
- ☆33Jul 31, 2024Updated last year
- ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery☆37Jun 23, 2026Updated 3 weeks ago
- 100G Udp Link For axi Stream☆16Jun 27, 2023Updated 3 years ago
- Mixture of Experts from scratch☆14Apr 12, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Repository for work on on Xilinx's matrix vector activation unit's RTL implementation. Documentation available at: https://asadalam.githu…☆20Jan 21, 2022Updated 4 years ago
- ThinK: Thinner Key Cache by Query-Driven Pruning☆30Jun 2, 2026Updated last month
- Research artifacts from Recursive's automated AI research system☆166Jun 11, 2026Updated last month
- A recommendation model kernel optimizing system☆12Jun 5, 2025Updated last year
- [COLM 2025] Official code for "When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoni…☆15Oct 31, 2025Updated 8 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆227Updated this week
- The open source implementation of the multi grouped query attention by the paper "GQA: Training Generalized Multi-Query Transformer Model…☆16Dec 11, 2023Updated 2 years ago