SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
☆152Nov 3, 2026Updated this week
Alternatives and similar repositories for SpecPilot
Users that are interested in SpecPilot are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention☆396Updated this week
- ☆23May 25, 2026Updated 5 months ago
- A 35B diffusion language model.☆144Oct 28, 2026Updated last week
- [NeurIPS 2026] dMoE: dLLMs with Learnable Block Experts☆50Oct 29, 2026Updated last week
- reproducing the flapping airplanes megakernel, in collab with magni☆129Updated this week
- 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.
- A paper list shared in the group meeting☆13Nov 13, 2025Updated 11 months ago
- A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a …☆24Updated this week
- [NeurIPS 2026] DMax: Aggressive Parallel Decoding for dLLMs☆131Sep 28, 2026Updated last month
- Flow Map Speculative Decoding☆56Updated this week
- Qwen3.5-2B with a SIMT GPU inside its weights, 45 compiled layers in front of Qwen’s own, using its Gated DeltaNet layers as registers an…☆117Updated this week
- Exact SGLang runtime for GLM-5.3-Flash-NVFP4 on 4x RTX PRO 6000 Blackwell (SM120): flashinfer_cutlass MoE, DSA+KDA attention, NEXTN MTP5,…☆17Aug 27, 2026Updated 2 months ago
- ☆27Aug 19, 2026Updated 2 months ago
- ☆21Aug 17, 2026Updated 2 months ago
- ☆30Updated this week
- 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.
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆22Mar 22, 2026Updated 7 months ago
- Offical implementation of "SpiLiFormer" (ICCV2025)☆11Jan 3, 2026Updated 10 months ago
- This is the della guide for Zhuang's group at Princeton University.☆14Mar 24, 2026Updated 7 months ago
- Map of K2 Horizon data code and datasets☆26Oct 23, 2026Updated 2 weeks ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- Flash Vision-Language-Action Inference for Autonomous Driving☆95Sep 15, 2026Updated last month
- Llama-architecture models (SmolLM2 135M, 360M, 1.7B) in Bend 2, token for token against PyTorch, with the shapes in the types☆16Updated this week
- ☆22Apr 3, 2026Updated 7 months ago
- Structure based DTI prediction using FSQ discretization☆17Apr 19, 2026Updated 6 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.
- Official Inference Code of EAGLE-4☆1,156Updated this week
- Official codebase for "Multi-Token Prediction Done Right"☆91Oct 30, 2026Updated last week
- WeChat official account crawler 微信公众号爬虫☆13Apr 13, 2024Updated 2 years ago
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆17May 25, 2026Updated 5 months ago
- [EMNLP 2026 Findings] The official code of Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior☆23Jan 6, 2026Updated 10 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- A model-agnostic GPU runtime for shipping models as verified programs.☆155Updated this week
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆30Oct 8, 2026Updated 3 weeks ago
- [ECCV 2026] Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models☆28Jun 20, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Stabilizing PPO in LLM post-training via robust critic learning https://arxiv.org/pdf/2609.36802☆25Updated this week
- ☆43Oct 30, 2026Updated last week
- A high performance batching router optimises max throughput for text inference workload☆16Sep 6, 2023Updated 3 years ago
- ☆20Dec 24, 2024Updated last year
- The official code of On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment☆29Oct 29, 2026Updated last week
- Qwen3.5-2B with a filesystem compiled and inserted directly into its weights.☆90Updated this week
- An LLM running on an NPU inside an LLM. Karpathy's stories260K writing stories on a vector unit compiled into Qwen3.5-4B's weights.☆123Updated this week