First public benchmark of llama.cpp speculative decoding on Qwen3.6-35B-A3B with a single RTX 3090 (post PR #19493 merge, 2026-04-19). 19 configurations covering ngram-cache, ngram-mod, and classic draft with vocab-matched Qwen3.5-0.8B. Finding: no variant achieves net speedup on Ampere + A3B MoE. Raw JSON, plots, full reproducibility.
☆31May 16, 2026Updated last month
Alternatives and similar repositories for qwen3.6-speculative-decoding-rtx3090
Users that are interested in qwen3.6-speculative-decoding-rtx3090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reproducible llama.cpp configs + per-category quality benches for Qwen3.6-27B on a single RTX 4090. Winners, dead ends, and the silent-co…☆22Apr 26, 2026Updated 2 months ago
- Updated voice agent with Nemotron 3.5 ASR☆15Jun 4, 2026Updated last month
- Install micromamba, and optionally create a base conda environment.☆10Apr 5, 2025Updated last year
- The code for paper "EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning"☆40Updated this week
- ☆22May 24, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- MD5 core in verilog☆13May 1, 2012Updated 14 years ago
- ☆34Mar 12, 2026Updated 4 months ago
- Links to all the source code and solutions I reference in my O'Reilly Introduction to Docker video tutorial☆11Dec 10, 2014Updated 11 years ago
- ☆10Jul 14, 2025Updated last year
- RPCNIC: A High-Performance and Reconfigurable PCIe-attached RPC Accelerator [HPCA2025]☆15Dec 9, 2024Updated last year
- ☆11Sep 11, 2024Updated last year
- ☆10Apr 29, 2023Updated 3 years ago
- Tests for at-import in CSS☆18May 16, 2026Updated last month
- Open5GS 5GC & UERANSIM UE / RAN Sample Configuration - Select UPF based on S-NSSAI☆14Apr 1, 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.
- Graph partitioning for distributed GNN training☆13Mar 26, 2023Updated 3 years ago
- Spline interpolation with FITPACK for xtensor.☆14Apr 10, 2018Updated 8 years ago
- Artifact for "DX100: A Programmable Data Access Accelerator for Indirection (ISCA 2025)" paper☆19Nov 6, 2025Updated 8 months ago
- Dockerfiles for FreeSurfer☆13Apr 10, 2026Updated 3 months ago
- Open-source AI acceleration on FPGA: from ONNX to RTL☆56Jun 4, 2026Updated last month
- Django catalog application. Manages tree organized models☆26May 12, 2016Updated 10 years ago
- pastescript template for a complete django project with pip+virtualenv, fabric, a gevent-based wsgi server and various helpers scripts. R…☆13Sep 29, 2010Updated 15 years ago
- Control fault/locate indicators in disk slots in enclosures (SES devices)☆13Mar 23, 2026Updated 3 months ago
- Code for "Practical Low-Rank Communication Compression in Decentralized Deep Learning"☆17Aug 4, 2020Updated 5 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Typescript utilities for input validation, with emphasis on security☆19Jan 3, 2024Updated 2 years ago
- Source code for the Real World React workshop☆10Sep 17, 2016Updated 9 years ago
- Code for a model-based version of Constrained Policy Optimization☆11May 6, 2021Updated 5 years ago
- A full-featured, hackable Next.js AI chatbot built by Vercel but running solely on a VPS, no outside APIs except for LLMs☆12Apr 16, 2024Updated 2 years ago
- LaTex code for creating my CV☆11Jul 5, 2019Updated 7 years ago
- [IPDPS 2024] Adaptive neighbor sampling for temporal GNN☆16Feb 17, 2025Updated last year
- Authentication Is Hard, Let's Ride Bikes PyCon 2013 presentation☆35Mar 16, 2013Updated 13 years ago
- ☆13Mar 25, 2021Updated 5 years ago
- A deep learning CNN model to predict diseases in plants using the famous AlexNet architecture☆12May 12, 2021Updated 5 years 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.
- Voice transcription for macOS with global hotkey support, multi-language, and AI-powered transcription (Groq & OpenAI)☆33Updated this week
- Fast LLM speculative inference server for consumer hardware.☆2,656Updated this week
- LIBRA: Enabling Workload-aware Multi-dimensional Network Topology Optimization for Distributed Training of Large AI Models☆12May 7, 2024Updated 2 years ago
- Tools for accessing open data sets published by the Allen Institute for Brain Sciences☆15Jun 29, 2021Updated 5 years ago
- Teacher - student distillation using DeepSpeed☆20Oct 7, 2022Updated 3 years ago
- Specialized fork for (relatively) fast single-GPU inference (in CUDA) using large MoE models that don't fit fully into VRAM☆16May 6, 2026Updated 2 months ago
- su su su supernova☆24Jan 9, 2025Updated last year