Strata port for Tesla V100 (sm_70): Qwen3.8-Flash-Next with 262K context and MTP
☆129Nov 6, 2026Updated this week
Alternatives and similar repositories for Strata-V100
Users that are interested in Strata-V100 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆260Sep 14, 2026Updated last month
- High-performance Duo-V100-GPU inference for selected model checkpoints and GPUs.☆37Updated this week
- A 198t/s and 353t/s qwen 3.8 27b inferencing engine for 2*v100 and 4*v100☆101Updated this week
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,477Updated this week
- 两张 V100 跑 Qwen3.8-27B 到 100 tok/s（186K 上下文）：重写 sm70 注意力内核 + 多卡张量并行。Fork of geoffwatts/ninfer-v100.☆18Sep 28, 2026Updated last month
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Hand-written NVFP4 W4A16 CUDA kernels for Volta☆181Aug 19, 2026Updated 2 months ago
- CUDA engine that splits every layer of a production quality MoE LLM across three PCIe V100 cards delivering 382 tok/s on a used $1,800 bo…☆64Updated this week
- Step-by-step guide to cross-flash the AMD Radeon Pro V620 to a Radeon Pro W6800 for display output, home-lab compatibility, and fan contr…☆16Sep 16, 2026Updated last month
- ☆24Jun 27, 2026Updated 4 months ago
- marlin_v100 是一个从 vLLM 主树中提取出来的最小 Marlin 独立开发工作区，聚焦于 Marlin dense 与 Marlin MoE 的源码开发、最小构建和轻量验证。它保留了核心 CUDA/C++ 实现、最小 Python 薄封装、生成器测试与主树回写…☆26Jul 2, 2026Updated 4 months ago
- Curated V100 SXM2 pin maps, two- and four-GPU NVLink connection plans, and connector-only KiCad resources toward an open-source carrier b…☆51Updated this week
- The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; bench…☆114Updated this week
- This is a fork of prismml-eng/llama.cpp + amesianx/turboquant with support for TurboQuant and prism-ml/ternary-bonsai-27b-gguf (2-bit).☆17Jul 16, 2026Updated 3 months ago
- Auto-built Docker image of 1Cat-vLLM for NVIDIA Tesla V100 (sm_70/Volta) with CUDA 12.8 — rebuilt daily when upstream releases☆12Jul 22, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Fork of llama.cpp Nvida Volta V100 (tensor parallelism 4 x v100 GPU)☆12Updated this week
- forked from vllm-project/flash-attention☆74May 9, 2026Updated 5 months ago
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆21Oct 16, 2026Updated 3 weeks ago
- NVIDIA Linux open GPU with P2P support☆16Jul 14, 2024Updated 2 years ago
- Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of …☆49Updated this week
- vLLM fork for Tesla V100☆15May 31, 2026Updated 5 months ago
- Recipe for running vLLM productively on Radeon PRO V620 (Navi 21 / gfx1030) on Linux. Multiple Qwen models supported.☆21Sep 6, 2026Updated 2 months ago
- Strata for a PC with two NVIDIA GPUs and 32 GB of RAM: the low-RAM mode on a layer split, both cards working at the same time. 143 tok/s …☆84Oct 6, 2026Updated last month
- Implementation of FlashAttention-2 for Nvidia Tesla V100 / Titan V☆217Updated this week
- 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.
- Run MoE models bigger than your RAM, without the speed cliff☆20Updated this week
- ☆23Sep 16, 2024Updated 2 years ago
- llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.☆60Oct 27, 2026Updated last week
- Single-card Intel Gaudi2 vLLM source snapshot: FP8 Qwen, non-greedy DFlash2/MTP, GDN kernels and host-side optimizations.☆17Updated this week
- 强大的ComfyUI API图像编辑自定义节点，支持多个API提供商。通过ModelScope、OpenRouter、OpenAI、Google Gemini等API实现文本生图、单图编辑和多图合成功能，具备动态模型加载和安全密钥管理能力。☆13Sep 3, 2025Updated last year
- Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- …☆2,632Updated this week
- FlashAttention brought back to Tesla V100 — a deep llama.cpp fork: SM 7.0 D256 kernels, SplitKV3, q4_0 KV cache, DFlash2 speculative deco…☆19Updated this week
- Toolkit for optimizing or building inference engines tailored to your hardware and desired LLM.☆44Updated this week
- Run Qwen3.8-Flash-Next on one AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). EXL3 4.05 and 3.05 bpw packs, own ROCm/HIP kernels, OpenAI-com…☆19Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- WavvieW: Analyzes the noise-wave-generator, synthesizer, audio files, input-mic_line-in with Oscilloscope and Spectrum FFT.☆20Jul 2, 2026Updated 4 months ago
- Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith …☆906Updated this week
- ModelScope API WebUI 基于ModelScope API的现代化Web应用，提供完整的AI模型服务访问界面。☆15Oct 2, 2025Updated last year
- ☆27Oct 19, 2026Updated 2 weeks ago
- What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here☆18Oct 12, 2026Updated 3 weeks ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆41,381Updated this week
- Simple 2-channel virtual oscilloscope (soundcard signal) - SDL, RtAudio, FFTW3☆12Mar 25, 2017Updated 9 years ago