vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several
☆18Oct 19, 2026Updated this week
Alternatives and similar repositories for vllm-cmp170hx
Users that are interested in vllm-cmp170hx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Tuning and qualification harness for the NVIDIA CMP 170HX (GA100). Measures, gates and recovers clock/voltage settings, and treats a comp…☆91Sep 28, 2026Updated 3 weeks ago
- 1Cat-vLLM on Intel Gaudi☆43Oct 12, 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
- glm-5.2 on too many 64 / 80 GB A100's☆22Sep 9, 2026Updated last month
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆89Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A tool to unlobotomize your NVIDIA card!☆32Sep 6, 2026Updated last month
- GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 482.6 tok/s single-user, up to 943.7 tok/s at 8 users, 262K context, TP4 or PP4, on…☆85Oct 16, 2026Updated last week
- Dogfooding vLLM backport for older GPUs.☆333Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆38Updated this 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 last week
- Linux P2P unlock and performance fixes for NVIDIA CMP 170HX☆41Sep 22, 2026Updated last month
- finetune the chain model based on cvte open source model without traing any GMM for frame alignment☆12Aug 6, 2020Updated 6 years 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
- 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
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Paste a story, get a film. A ComfyUI node pack that plans a story into shots, casts it with Krea2 reference sheets, and renders it with M…☆21Aug 29, 2026Updated last month
- vllm混合推理扩展插件，支持多NUMA混合推理，单卡推理Qwen3-Next模型可达1000+ prefill☆34Nov 7, 2025Updated 11 months ago
- Turn one prompt into a finished MP4. An AI agent skill for Claude Code, Cursor, Codex & Windsurf that generates TikTok/Reels/Shorts, YouT…☆32Jun 17, 2026Updated 4 months ago
- A powerful and fully customizable Discord bot designed for server administration. Featuring advanced moderation tools, a ticketing system…☆24Mar 25, 2026Updated 6 months ago
- 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 3 weeks ago
- My (miniature) version of Samy Kamkar's magspoof project☆11Aug 14, 2019Updated 7 years ago
- Magnetic card spoofer☆12May 5, 2014Updated 12 years ago
- A tool to unlobotomize your NVIDIA card!☆791Oct 8, 2026Updated 2 weeks ago
- A visual library for exploring and comparing Krea 2 prompt styles across base prompt scenes, generated locally with ComfyUI.☆17Oct 11, 2026Updated last week
- 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.
- My aider prompt for 'Precision prompting' approach.☆12May 2, 2025Updated last year
- Embed widgets in your Notion pages easily☆17Oct 31, 2024Updated last year
- Arduino code to run the Coda Kerbal Controller Mk3.☆10Jun 14, 2023Updated 3 years ago
- A fork of jasl/vllm (codex/ds4-sm120-min-enable) with CPU-GPU hybrid inference support for DeepSeek-V4 on SM120+.☆31Sep 10, 2026Updated last month
- A cmpunlocker fork with working p2p on SYS-4028GR-TRT2☆26Aug 8, 2026Updated 2 months ago
- Wireless magnetic card emulation☆15Sep 21, 2019Updated 7 years ago
- Enter, track, cherish. Look back at your best moments with Memory. iOS-first mood tracker & diary app built using React Native, React Nav…☆13Oct 20, 2022Updated 4 years ago
- Node.js package for finding and removing duplicate image files with extreme precision☆11Jun 10, 2018Updated 8 years ago
- ☆64Aug 6, 2026Updated 2 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.
- Caress is a revolutionary mental health app designed to streamline therapy processes and promote holistic well-being.☆12Oct 1, 2023Updated 3 years ago
- File-based named channels for talking between AI coding agents (Claude Code, Codex, OpenCode) across sessions — zero-server, kqueue-backe…☆25Sep 11, 2026Updated last month
- Recreated gerbers for the Supermicro X11SSH-F motherboard.☆19Aug 2, 2023Updated 3 years ago
- An integration that provides free, unlimited two-way synchronization between Google Calendar and Notion.☆15Oct 26, 2024Updated last year
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆10Nov 19, 2024Updated last year
- MCP server for file operations on non-UTF-8 text: detects the encoding from the bytes, hands the model UTF-8, and writes back in the orig…☆26Updated this week
- AI Agent Engine/Harness/TUI with Zero Dependencies☆26Jul 30, 2026Updated 2 months ago