Sequential Monte Carlo Speculative Decoding
☆53Aug 25, 2026Updated 2 months ago
Alternatives and similar repositories for smcsd
Users that are interested in smcsd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆27May 12, 2026Updated 6 months ago
- Measuring machine TFLOPS using pytorch.☆14Dec 9, 2025Updated 11 months ago
- Tile primitives for speedy kernels☆21Sep 13, 2026Updated 2 months ago
- Production LLM inference on the Apple Neural Engine — a practitioner's guide, complete with converters, Swift runtimes, and validated mod…☆47Jun 7, 2026Updated 5 months ago
- Scripts for training Qwen 2.5 VL with ms-swift and GRPO☆13Feb 27, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention☆25May 25, 2026Updated 5 months ago
- Truthful scheduler-step and streaming visualization for local LLM inference☆36Sep 6, 2026Updated 2 months ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆11Updated this week
- GPU cold boot optimization using NVIDIA cuda-checkpoint + CRIU — snapshot and restore a live GPU process including compiled kernels and v…☆11Jun 4, 2026Updated 5 months ago
- ☆18Sep 27, 2026Updated last month
- Experimental validation: Agentic Search (context trees) vs traditional RAG for code retrieval. Agentic wins with 99% fewer tokens and 2× …☆13Jan 6, 2026Updated 10 months ago
- Code for Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers (https://arxiv.org/abs/2606.31779)☆55Jul 20, 2026Updated 3 months ago
- Turn an authenticated X feed into NotebookLM-ready source bundles and podcast inputs.☆10Apr 8, 2026Updated 7 months 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.
- MetaEase is an extension of the MetaOpt project that allows you to analyze the code you have to find its optimality gap.☆14Apr 13, 2026Updated 6 months ago
- Triton kernels for dynamic causal short convolutions.☆35Jun 4, 2026Updated 5 months ago
- GIt Smart HTTP Server Rack Implementation with token-based authentication support☆12Apr 19, 2014Updated 12 years ago
- ☆396Apr 16, 2026Updated 6 months ago
- Plug-and-play PyTorch transformer research framework. Swap attention, FFN, norm, positional, connection, projection, optimizer, scheduler…☆18Oct 25, 2026Updated 2 weeks ago
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated 2 years ago
- [NeurIPS 2025] Speculate Deep and Accurate☆25Aug 10, 2026Updated 3 months ago
- Code for the paper "Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning" https://arxiv.org/abs/2609.03430☆75Sep 4, 2026Updated 2 months ago
- Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought☆20Feb 10, 2026Updated 9 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆14Apr 13, 2026Updated 6 months ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 6 months ago
- A flexible Monte Carlo Tree Search framework with PyTorch for decision-making in language models.☆12Feb 23, 2025Updated last year
- Implementation for our paper "Gradient Regularization prevents Reward Hacking in RLHF and RLVR". Implemented TRL and for Huggingface Tran…☆12Feb 24, 2026Updated 8 months ago
- ☆41Aug 16, 2026Updated 2 months ago
- alternative way to calculating self attention☆18May 25, 2024Updated 2 years ago
- ☆51Jul 3, 2026Updated 4 months ago
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆211Apr 21, 2026Updated 6 months ago
- The official repository of Quamba1 [ICLR 2025] & Quamba2 [ICML 2025]☆70Jun 19, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- High-performance tokenization for inference☆15Nov 3, 2026Updated last week
- ☆17Oct 7, 2026Updated last month
- Dynamic per-token early exit for LLM inference. Skip layers tokens don't need☆34Sep 18, 2026Updated last month
- Sample-Efficient Parametric Learning from Natural Language☆13Feb 5, 2026Updated 9 months ago
- This is the official code for the paper "Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models".☆14May 7, 2026Updated 6 months ago
- ☆17Jun 15, 2026Updated 4 months ago
- InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem☆11Dec 8, 2025Updated 11 months ago
Are these results useful?