Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"
☆30Apr 17, 2026Updated 4 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:
- ☆78Apr 30, 2026Updated 4 months ago
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆20May 20, 2026Updated 3 months ago
- XoRL☆46Sep 5, 2026Updated last week
- A simple, fast and robust program-aware agentic inference system.☆442Jul 5, 2026Updated 2 months ago
- ☆28Jun 1, 2026Updated 3 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Lightweight harness for replaying inference traffic against an endpoint☆26Aug 1, 2026Updated last month
- ☆16May 27, 2026Updated 3 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆75Oct 2, 2025Updated 11 months ago
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆103Jul 26, 2026Updated last month
- Opensource code for ICML 2026 poster☆16Nov 26, 2025Updated 9 months ago
- DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning☆19Nov 11, 2025Updated 10 months ago
- Awesome-RL-Reasoning☆17Aug 26, 2026Updated 2 weeks ago
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inference☆15May 19, 2026Updated 3 months ago
- Checkpointable dataset utilities for foundation model training☆32Jan 29, 2024Updated 2 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.
- Official Code Repositiry for "RaDeR: Reasoning-aware Dense Retrieval Models" accepted at Main Conference EMNLP 2025☆18Jun 23, 2025Updated last year
- ☆154Apr 15, 2026Updated 4 months ago
- The training codes of Jasper-Token-Compression-600M☆22Nov 19, 2025Updated 9 months ago
- [Tech Report] Expanded Hyper-Connections☆62Jul 21, 2026Updated last month
- ☆24Jun 16, 2026Updated 2 months ago
- [COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficien…☆24Aug 23, 2026Updated 3 weeks ago
- ☆20Sep 16, 2025Updated 11 months ago
- Repository for "Training Language Models To Explain Their Own Computations"☆37Jul 7, 2026Updated 2 months ago
- Advancing the frontier of efficient AI☆69Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [ICML2026] Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization☆65Jul 26, 2026Updated last month
- Gemini evaluations☆26Sep 3, 2026Updated last week
- The code for paper "MemGym: a Long-Horizon Memory Environment for LLM Agents".☆21Jun 2, 2026Updated 3 months ago
- ☆18Sep 23, 2025Updated 11 months ago
- A PYNQ overlay demonstrating the Xilinx RFSoC SD-FEC☆13Sep 2, 2026Updated last week
- ☆50Apr 1, 2026Updated 5 months ago
- Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization☆23Feb 18, 2026Updated 6 months ago
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆21Jan 24, 2025Updated last year
- ☆93Jun 20, 2025Updated last year
- 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.
- VidKV: Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models☆25Mar 26, 2025Updated last year
- Framework based on Partial Reconfiguration for chip characterization utilizing ring-oscillator PUFs☆14Apr 1, 2020Updated 6 years ago
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆34Feb 17, 2024Updated 2 years ago
- [ICML 2026] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs☆34Apr 27, 2026Updated 4 months ago
- ☆32Mar 24, 2025Updated last year
- A fork of llama3.c used to do some R&D on inferencing☆24Dec 20, 2024Updated last year
- PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation [NeurIPS 2025]☆19Oct 11, 2025Updated 11 months ago