在四卡A100上适配Sglang部署deepseek-v4-flash正式版模型
☆14Aug 2, 2026Updated 3 months ago
Alternatives and similar repositories for deepseek-v4-a100-sglang-v0516
Users that are interested in deepseek-v4-a100-sglang-v0516 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek-V4.1-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 297 tok/s for one user, up to 868 tok/s at eight, 262K context, one-command c…☆25Nov 2, 2026Updated last week
- 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 3 weeks ago
- Dogfooding vLLM backport for older GPUs.☆360Nov 3, 2026Updated last week
- 适配泰安S8030显卡机自动调节系统风扇组件☆13Dec 13, 2024Updated last year
- Agent Doris CLI☆17May 30, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆70Nov 4, 2026Updated last week
- Linux P2P unlock and performance fixes for NVIDIA CMP 170HX☆39Sep 22, 2026Updated last month
- dsv41-flash-pp5-170hx &pp6 Supports the original (full/unquantized) model. Prefill 7,000 t/s, decode 45-75-125 t/s. dspark. Requires 200 …☆13Nov 2, 2026Updated last week
- ICDO: International Classification of Diseases Ontology☆12Apr 19, 2024Updated 2 years ago
- Qwen3.8-27B INT8 + DFlash2 on a rented CMP 170HX — failure analysis (private GHCR image prevented benchmark)☆17Aug 30, 2026Updated 2 months ago
- React client SDK for Casdoor☆18Oct 3, 2026Updated last month
- 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
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆10Nov 19, 2024Updated last year
- 脚本编写的工具集。☆19Sep 10, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- glm-5.2 on too many 64 / 80 GB A100's☆22Sep 9, 2026Updated 2 months ago
- 🚅 FastCopy is a remote file copy program similar to scp. It uses concurrent transmission, so the speed is faster than scp.☆28Aug 14, 2026Updated 2 months ago
- An example repo to demo how to integrate python-cas into a fastapi app.☆16Sep 13, 2021Updated 5 years ago
- ☆22Feb 25, 2026Updated 8 months 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…☆20Sep 18, 2026Updated last month
- 带AC自动机的C++Trie树实现，支持UTF8和GBK编码☆14Jun 16, 2020Updated 6 years ago
- FastAPI WebSocket server for the OpenVoice text-to-speech model.☆12Jun 6, 2024Updated 2 years ago
- X64Dbg的Model Context Protocol服务器，用于AI辅助逆向分析和调试。☆22Sep 17, 2026Updated last month
- Tested recipes, runtime fixes, kernels and fleet practices for serving LLMs with vLLM on Intel Gaudi☆12Oct 25, 2026Updated 2 weeks 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.
- empow's intent classification plugin☆11Jun 27, 2019Updated 7 years ago
- Python FastAPI & Template & vanilla JS application example based on casdoor-python-sdk and casdoor-js-sdk☆22Oct 6, 2026Updated last month
- 一个基于GTCEu的整合包，由于制作组内部冲突，现已存档。☆24Sep 3, 2022Updated 4 years ago
- The document for pdfdeal☆28Feb 20, 2025Updated last year
- ☆17Oct 15, 2023Updated 3 years ago
- configuration files on a Mac☆22Nov 3, 2026Updated last week
- OpenCore EFI for X79 Mainboard and CPU xeon E5 2650v2 RX470☆20Feb 1, 2021Updated 5 years ago
- NInfer SM80 port for NVIDIA CMP 170HX☆29Aug 22, 2026Updated 2 months ago
- triton3.2.0添加mi25/mi50/mi60支持☆14Apr 26, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 🛠 My rc files and other configs. Includes: Bash, Zsh, Vim, Tmux, Git, Terminal (macOS), VS Code☆38Updated this week
- A simple mock server, more easy to deploy and easy to use. It is base on express and ant-design.☆13Jun 12, 2018Updated 8 years ago
- Simple Django app to provide API Gateways for micro-services☆20Sep 10, 2017Updated 9 years ago
- Panther X2 (RK3566, ex-Helium hotspot) as a Linux board: Buildroot + Rockchip 6.12 kernel, SX1302 LoRa gateway (ChirpStack), UVC camera -…☆17Oct 27, 2026Updated 2 weeks ago
- Two composable skills that turn a PowerPoint template into a freshly filled deck — without an agent ever hand-reading shape indices off a…☆44Jun 12, 2026Updated 4 months ago
- vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several☆27Nov 2, 2026Updated last week
- DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallel…☆118Aug 13, 2026Updated 2 months ago
Are these results useful?