Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/disk KV offload, and MTP or DFlash2 speculative decoding.
☆62Nov 17, 2026Updated this week
Alternatives and similar repositories for ReVolta
Users that are interested in ReVolta are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Agentic-coding focused inference engine for n x V100 (e.g. SXM2), based on SGLang: GLM-5.3-Flash, Qwen3.8-Flash-Next, DeepSeek-V4.1-Flash…☆42Updated this week
- 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…☆83Updated this week
- SGLang for cool dudes using V100☆86Updated this week
- ComfyUI MiniMax H3 inference optimizations for NVIDIA Tesla V100 (SM70)☆36Sep 29, 2026Updated last month
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,533Updated this week
- 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.
- NInfer on Tesla V100 (sm_70): Qwen3.8-27B deployment, build/convert scripts, systemd service, and cross-engine benchmark (vs llama.cpp). …☆56Sep 15, 2026Updated 2 months ago
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆25Jul 10, 2026Updated 4 months ago
- 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
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆273Sep 14, 2026Updated 2 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 last month
- 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…☆125Updated this week
- 1Cat-vLLM on Intel Gaudi☆48Oct 12, 2026Updated last month
- Exact LLM inference engine written from scratch for AMD Strix Halo (gfx1151, ROCm/HIP). Qwen3.8-Flash-Next on one node or two replicas; D…☆33Updated this week
- Third party commentaries for UniqueBible☆13Apr 8, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 1Cat Studio: unified vLLM workbench, Codex Agent and creative canvas☆15Nov 6, 2026Updated last 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…☆33Updated this week
- 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…☆61Aug 8, 2026Updated 3 months ago
- Huggingface but for inference engines.☆15Updated this week
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆101Nov 9, 2026Updated last week
- A deterministic inference engine for running large models on a single AMD Strix Halo 128 GB☆25Updated this week
- 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 8 months ago
- Known-good vLLM recipe: Qwen3.8-27B-Int8 + MTP speculative decoding on NVIDIA CMP 170HX 64GB (Hynix) — 84 tok/s, 262k ctx☆13Oct 8, 2026Updated last month
- 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.
- ☆19Updated this week
- Single-card Intel Gaudi2 vLLM source snapshot: FP8 Qwen, non-greedy DFlash2/MTP, GDN kernels and host-side optimizations.☆19Updated this week
- LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context☆106Updated this week
- ☆17Jun 10, 2026Updated 5 months ago
- FlashAttention brought back to Tesla V100 — a deep llama.cpp fork: SM 7.0 D256 kernels, SplitKV3, q4_0 KV cache, DFlash2 speculative deco…☆19Nov 8, 2026Updated last week
- 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…☆27Jul 2, 2026Updated 4 months ago
- Low-cost (approx. 1000R) biaxial equatorial mount using dual S14-100/S17-100 harmonic reducers, 1:5.18 planetary reducers, 42H48 stepper …☆15Aug 26, 2024Updated 2 years ago
- Run local LLMs on a Tesla V100-SXM2-16GB: prebuilt binaries, serve scripts, and setup for Windows and Linux (Qwen3 + Gemma 4, Claude Code…☆20Sep 1, 2026Updated 2 months ago
- Fast vLLM on AMD Strix Halo: one docker command for Qwen, Gemma, LFM and more, up to 31x faster prefill and ~2x decode vs stock vLLM at l…☆21Nov 8, 2026Updated last week
- 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.
- ☆11Feb 11, 2015Updated 11 years ago
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆60Nov 7, 2026Updated last week
- Qwen3.8-Flash-Next (176B MoE) on a single RTX PRO 6000 Blackwell 96GB — NVMe-streamed PLE table, CUDA graphs with NEXTN speculation, meas…☆10Aug 28, 2026Updated 2 months ago
- 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.☆21Sep 28, 2026Updated last month
- Firmware that drives the 2nd generation Afridev Sensor☆15May 7, 2021Updated 5 years ago
- DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) — up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2☆21Aug 28, 2026Updated 2 months ago
- Deterministic PyGhidra extraction, triage, and local LLM compiler-backend pipeline for C reimplementation.☆11Oct 18, 2026Updated last month
Are these results useful?