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映射，适合在不受主树全量构建干扰的情况下快速重构和验证 Marlin 相关改动。
☆26Jul 2, 2026Updated 4 months ago
Alternatives and similar repositories for marlin_v100
Users that are interested in marlin_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:
- Block-FP8 (W8A16) on NVIDIA V100 / Volta (sm_70) for vLLM — the FP8 path upstream drops on Volta, tuned for sparse MoE.☆15Jul 10, 2026Updated 4 months ago
- vLLM fork for Tesla V100☆15May 31, 2026Updated 5 months ago
- This project is specifically developed for V100, based on lmdeploy 0.12.1, and supports mainstream open-source models from Q4 2025 to Q1 …☆22Mar 18, 2026Updated 7 months ago
- SGLang for cool dudes using V100☆86Updated this week
- 1CatV2 with TileLANG written FA-v100 and many goodies☆20Jul 15, 2026Updated 3 months ago
- 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.
- The world-first Pearl miner for Ascend NPU.☆10Jul 20, 2026Updated 3 months ago
- 1Cat-vLLM on Intel Gaudi☆47Oct 12, 2026Updated last month
- Hand-written NVFP4 W4A16 CUDA kernels for Volta☆185Aug 19, 2026Updated 2 months ago
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,494Updated this week
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆24Jul 10, 2026Updated 4 months ago
- 1Cat Studio: unified vLLM workbench, Codex Agent and creative canvas☆15Updated this week
- Mixed-precision acceleration patch for MiniMax H3 inference on NVIDIA V100☆40Sep 6, 2026Updated 2 months ago
- Run MiniMax H3 at native fp16 on pre-bf16 GPUs (V100/Volta) — exact-math fix for the black-frame overflows, ~11× faster than the fp32 fal…☆59Aug 8, 2026Updated 3 months ago
- Local LLM Inference Speed Test Tool☆252Oct 21, 2026Updated 3 weeks ago
- 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.
- ComfyUI MiniMax H3 inference optimizations for NVIDIA Tesla V100 (SM70)☆33Sep 29, 2026Updated last month
- Traverse, profiling and benchmarking. A toolbox for processor/accelerator evaluation.☆10Oct 5, 2026Updated last month
- 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
- A 198t/s and 353t/s qwen 3.8 27b inferencing engine for 2*v100 and 4*v100☆114Updated this week
- ComfyUI custom node: run MiniMax H3 at near-fp16 speed with near-fp32 numerical stability on GPUs without bf16/fp8 hardware (V100 sm_70)☆20Updated this week
- Community maintained hardware plugin for vLLM on Intel Gaudi☆68Updated this week
- C++ library for accessing smart cards using the PC/SC API☆11May 14, 2024Updated 2 years ago
- High-performance Duo-V100-GPU inference for selected model checkpoints and GPUs.☆40Nov 2, 2026Updated last 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
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆266Sep 14, 2026Updated last month
- [SMPPSim](http://www.seleniumsoftware.com/downloads.html) simulator docker image.☆11Jan 9, 2024Updated 2 years ago
- llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefil…☆78Updated this week
- Windows desktop screenplay writing app with Chinese-first UI, Hollywood formatting, FDX support, and local export tools.☆16Updated this week
- Voice typing for Windows. local & cloud ASR (Seed-ASR 2.0 )豆包语音输入法,FireRedASR2,Qwen audio/ASR,microsoft/mai-transcribe-2,MIMO ASR☆20Updated this week
- vllm for pascal☆12Nov 22, 2025Updated 11 months ago
- Disable DSE and WinTcb (without breaking DRM)☆11Aug 14, 2016Updated 10 years ago
- docker image for SMPP simulator from http://www.seleniumsoftware.com/☆15Jun 4, 2019Updated 7 years ago
- llama-cpp support turboquant and gemma 4☆20May 19, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- branch of OpenJCVM☆17Jan 3, 2014Updated 12 years ago
- multilingual RAG☆15Feb 6, 2024Updated 2 years ago
- TensorDB: In-Database Tensor Manipulation with Tensor-Relational Query Plans☆21Jul 25, 2014Updated 12 years ago
- xllama.cpp — Optimized LLM Inference for NVidia Tesla V100-SXM2-32GB☆18Apr 29, 2026Updated 6 months ago
- ☆13Dec 24, 2025Updated 10 months ago
- 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 last year
- NVIDIA Tesla V100 显卡驱动自动化管理套件☆34Oct 9, 2025Updated last year
Are these results useful?