vLLM 0.32 fork for consumer GPUs: 3 x 262K sessions on 4x RTX 3090, Qwen 3.8 Flash-Next at 184 tok/s, up to 17 on bigger cards. Seven checkpoints incl. Qwen3.8-27B, Nemotron 3.5 Super VL (1M) and Ornith 1.5. One command: merlin serve.
☆20Oct 22, 2026Updated last week
Alternatives and similar repositories for merlin-engine
Users that are interested in merlin-engine are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Linux P2P unlock and performance fixes for NVIDIA CMP 170HX☆40Sep 22, 2026Updated last month
- Raw benchmark logs for Swift-Qwen3.8-27B vs the Qwen3.8-27B BF16 base: every response, score, and config across 9 benchmarks☆13Sep 13, 2026Updated last month
- Async PLE SSD offload for Qwen3.8 Flash Next on a 64 GiB SM80 GPU: vLLM patch, setup guide, and measured PP/TG results.☆22Sep 24, 2026Updated last month
- Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,86…☆129Oct 15, 2026Updated 2 weeks ago
- Qwen3.8-Flash-Next (W4A16) on 2x CMP 170HX: 110 tok/s decode, 7K prefill, 800 tok/s @ 23 concurrent - runs on 38 GB home RAM, no pinned m…☆21Sep 18, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- This is the implementation of the 4th place solution (yu4u's part) for RSNA 2024 Lumbar Spine Degenerative Classification at Kaggle.☆10Oct 11, 2024Updated 2 years ago
- Not insane. Designed to read WDB files from the latest World of Warcraft builds and output CSV files. Could be used as a library by other…☆15Sep 27, 2025Updated last year
- Serving Qwen3.8-27B at ~140 tok/s on 2x AMD R9700 in a Proxmox VM — with working GPU P2P (emulated PCIe switch + XanMod kernel + NDEBUG R…☆21Sep 16, 2026Updated last month
- A cmpunlocker fork with working p2p on SYS-4028GR-TRT2☆26Aug 8, 2026Updated 2 months ago
- Telenot Adapter☆10Sep 29, 2026Updated last month
- The accompany backend for PAI app☆12Mar 24, 2025Updated last year
- ☆10May 1, 2025Updated last year
- 双 SM80 / CMP 170HX 的 Qwen3.8-Flash-Next 社区 vLLM：NVIDIA NVFP4、GDS、TEP2、MTP6，支持 1～10 并发，词表与 PCIe 通信优化。中英文部署与可构建源码。☆28Oct 15, 2026Updated 2 weeks ago
- ☆18Aug 26, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- NInfer SM80 port for NVIDIA CMP 170HX☆29Aug 22, 2026Updated 2 months ago
- ICPR2022: Dynamic Data Augmentation with Gating Networks for Time Series Recognition☆11Jul 28, 2022Updated 4 years ago
- Variant for Visual GPT with better UI using h2o Wave & Single GPU support☆15Mar 12, 2023Updated 3 years ago
- Matthews Correlation Coefficient Loss implementation for image segmentation.☆12Mar 19, 2026Updated 7 months ago
- Efficient Mask-Aware Distributed Attention for Long-Context Training☆56Oct 16, 2026Updated last week
- DeepSeek-V4.1-Flash (764B) on 4×CMP 170HX: PP4 + shadow KV + EXL3 2bpw + DSpark + 512k ctx + native vision — patches, recipes, acceptance…☆15Sep 29, 2026Updated last month
- ☆11Sep 16, 2025Updated last year
- [CVPR2023] Official implementation of Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions☆14May 29, 2023Updated 3 years ago
- ☆10Dec 3, 2022Updated 3 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.
- Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a sep…☆49Jul 7, 2026Updated 3 months ago
- Official implementation of the paper "PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space"☆17May 6, 2026Updated 5 months ago
- Winning 3rd Place solution for HubMap - Hacking the Human Vasculature hosted on Kaggle☆16Aug 10, 2023Updated 3 years ago
- Dragonflight_Dekk-Core☆19Dec 23, 2023Updated 2 years ago
- OpenHands automation service☆44Updated this week
- Simple RAM benchmark for Linux.☆12Aug 4, 2021Updated 5 years ago
- This project explores the use of artificial intelligence to generate realistic non-player characters (NPCs) in a virtual village environm…☆20Oct 9, 2025Updated last year
- Python library to create bank statements in the MT940 format☆14Mar 1, 2026Updated 7 months ago
- Matching The Statements: A Simple and Accurate Model for Key Point Analysis (ArgMining | EMNLP 2021)☆12Feb 11, 2022Updated 4 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Simple kalman filter using opencv for 3D tracking☆14May 27, 2017Updated 9 years ago
- ☆19Sep 19, 2022Updated 4 years ago
- A test docker setup for running Qwen Code on StrixHalo☆18Feb 12, 2026Updated 8 months ago
- ☆18Jan 9, 2023Updated 3 years ago
- Linux /proc data in a consistent, parsed format.☆10Mar 28, 2016Updated 10 years ago
- ☆13Mar 26, 2026Updated 7 months ago
- My personal wezterm configuration☆16Dec 20, 2024Updated last year