Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design
☆26May 29, 2025Updated last year
Alternatives and similar repositories for SpecMQuant
Users that are interested in SpecMQuant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆56Jul 15, 2025Updated last year
- Source codes for paper "BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity".☆19Jan 10, 2026Updated 8 months ago
- SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts☆68Dec 1, 2025Updated 10 months ago
- ☆18Apr 7, 2025Updated last year
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆75Apr 25, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆42Mar 28, 2024Updated 2 years ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆29Apr 15, 2025Updated last year
- Implementation of Sketch Your Own GAN in Jittor☆10Jan 2, 2022Updated 4 years ago
- ☆14Oct 3, 2024Updated 2 years ago
- Federated Conformal Prediction with Quantile-of-Quantiles (FedCP-QQ)☆11May 6, 2026Updated 5 months ago
- 面向大模型的民族文化数据集☆17May 26, 2025Updated last year
- ☆104Feb 11, 2026Updated 7 months ago
- LightRFT (Light Reinforcement Fine-Tuning) is an advanced reinforcement learning fine-tuning framework designed for Large Language Models…☆19Jan 12, 2026Updated 8 months ago
- Implementation of AdaCQR(COLING 2025)☆15Dec 30, 2024Updated 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.
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆243Jan 14, 2026Updated 8 months ago
- ☆69Dec 3, 2024Updated last year
- Learning and Debugging for FSDP/FSDP2 Training☆18Feb 7, 2026Updated 8 months ago
- Repository for "TESS-2: A Large-Scale, Generalist Diffusion Language Model"☆59Feb 20, 2025Updated last year
- Matrix Accelerator Generator for GeMM Operations based on SIGMA Architecture in CHISEL HDL☆15Mar 21, 2024Updated 2 years ago
- AI Code Reviewer Platform with BYOK☆17Updated this week
- ☆10Feb 12, 2020Updated 6 years ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,204Updated this week
- 2SSP: A Two-Stage Framework for Structured Pruning of LLMs☆22Aug 18, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Efficient Conformal Prediction via Cascaded Inference with Expanded Admission☆20Sep 15, 2021Updated 5 years ago
- Non-autoregressive Translation by Learning Target Categorical Codes☆11Jul 11, 2021Updated 5 years ago
- ☆12Apr 25, 2025Updated last year
- (ACL2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆37May 28, 2025Updated last year
- Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation☆44Jan 9, 2024Updated 2 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆160Dec 4, 2024Updated last year
- LLamaHTML is a simple html file to communicate with a running llamacpp llama-server☆25Aug 5, 2025Updated last year
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆32Feb 17, 2025Updated last year
- Code for "Simulated Multiple Reference Training Improves Low-Resource Machine Translation"☆15Dec 1, 2020Updated 5 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Simple and efficient memory pool is implemented with C++11.☆10Jun 2, 2022Updated 4 years ago
- Learning to Skip the Middle Layers of Transformers☆17Aug 7, 2025Updated last year
- AirLLM 70B inference with single 4GB GPU☆21Jun 27, 2025Updated last year
- ☆14Sep 7, 2024Updated 2 years ago
- Building autonomous driving system by using CARLA simulator☆11Apr 30, 2024Updated 2 years ago
- ☆13Mar 5, 2023Updated 3 years ago
- Implementation of LPLR algorithm for matrix compression☆33Nov 21, 2023Updated 2 years ago