DeepSeek-V4-Flash W4A16-FP8 quantization on 8x H200 — patches, recipe, mission report
☆14Sep 26, 2026Updated last month
Alternatives and similar repositories for dsv4-flash-w4a16-fp8
Users that are interested in dsv4-flash-w4a16-fp8 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MiniMax-M3 (MXFP4, MSA) serving on SM120 (RTX PRO 6000 Blackwell) — patched vLLM image + launch recipe, 192K context☆22Jun 15, 2026Updated 4 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆22Oct 21, 2026Updated last week
- Reproducible SGLang image for DeepSeek-V4-Flash-0731 on SM120☆37Aug 25, 2026Updated 2 months ago
- A query tool for HashiCorp Vault☆10Jun 26, 2024Updated 2 years ago
- ☆13Jul 23, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A living AI civilisation you can watch: tiny creatures discover, build, teach and pass knowledge on, with any LLM in their minds.☆24Oct 17, 2026Updated last week
- Numerical experiments on Jacobi SVD algorithm☆10Jun 3, 2018Updated 8 years ago
- Interface between Openfermion and Dirac to perform relativistic quantum chemistry calculations simulated on a quantum computer☆14Aug 12, 2022Updated 4 years ago
- Open Source TypeScript SDK for building real-time multimodal voice & vision AI agents☆28Jul 12, 2026Updated 3 months ago
- This is a tutorial prepared for a summer school in Changsha in 2021☆11Jul 15, 2021Updated 5 years ago
- Generates kid-friendly weather forecasts suitable for display on a large monitor. Uses OpenWeatherMap and a local or hosted LLM.☆17Feb 28, 2026Updated 8 months ago
- ThereminQ CLassiQ - QuantOPS : Orchestrate Qrack, Bonsai, Qimcifa and Tipsy in OpenCL, VCL and CUDA with an X WebUI☆14Jan 10, 2026Updated 9 months ago
- A [Genshin Impact] artifacts enhancement predictor. 一个【原神】圣遗物强化预测工具。☆13May 18, 2022Updated 4 years ago
- Local LLM proxy, DevOps friendly☆14Oct 11, 2026Updated 2 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- give me a toml configuration file, I'll give you export MY_ENV=foo☆10Jul 6, 2018Updated 8 years ago
- a Python3 library for ML modeling materials properties☆10Sep 15, 2019Updated 7 years ago
- Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — …☆85Jul 13, 2026Updated 3 months ago
- Code to reproduce experiments from the paper "Continual Pre-Training Mitigates Forgetting in Language and Vision" https://arxiv.org/abs/2…☆22Oct 23, 2023Updated 3 years ago
- Aurelia custom element that takes (server- or client side) generated html and compiles it into a fully functional Aurelia View☆12Nov 12, 2018Updated 7 years ago
- do some exercise☆15Dec 2, 2025Updated 10 months ago
- coro-http from Lit converted to work with plain Lua + Luv☆11Sep 7, 2021Updated 5 years ago
- A poor man's density functional theory program☆14May 18, 2026Updated 5 months ago
- The repository targets the OpenCL gemm function performance optimization. It compares several libraries clBLAS, clBLAST, MIOpenGemm, Inte…☆18Mar 28, 2019Updated 7 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Implementation of Squeeze-and-Excitiation Network on Keras☆22Sep 22, 2019Updated 7 years ago
- SGLang 0.5.21 for Qwen3.8-Flash-Next on one RTX PRO 6000: 264.5 tok/s decode, W4A16 routed experts (KLD 0.0111 vs BF16), 262K context, ex…☆17Updated this week
- A toolkit for optimizing machine learning models for practical applications☆32Mar 6, 2025Updated last year
- CAD files for DDR5 RDIMM cooling☆16Jun 12, 2025Updated last year
- An enhanced implementation for observable and bindable decorator of Aurelia☆16May 4, 2022Updated 4 years ago
- Aurelia async bindingbehavior to consume Observables and Promises☆17Jan 9, 2023Updated 3 years ago
- A plugin for declaring deep/shallow computed observation☆15Jan 7, 2023Updated 3 years ago
- A LinearOperator implementation for PyTorch☆18Jan 15, 2021Updated 5 years ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆38Updated 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.
- Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and SM120 (RTX PRO 6000) with vLLM☆198Updated this week
- A small collection of Quantum Phase Estimation algorithms coded in python using IBM's qiskit library.☆12Nov 25, 2021Updated 4 years ago
- Master the essential steps of pretraining large language models (LLMs). Learn to create high-quality datasets, configure model architectu…☆27Aug 7, 2024Updated 2 years ago
- 一个Turing专用vLLM分支，通过整合FlashInfer 0.6.18（PR #3526）与SM75后端门槛补丁（PR #47949），持续同步vLLM主线最新版本☆36Oct 11, 2026Updated 2 weeks ago
- ☆37Apr 26, 2026Updated 6 months ago
- ☆31Sep 11, 2024Updated 2 years ago
- Production-ready Open WebUI extensions, including Tools, Filters, Pipes, Actions, and Events for agent workflows, RAG, learning, automati…☆35Sep 25, 2026Updated last month