Unlock full speed FP16 tensor core of NVIDIA Turing GPUs
☆362Oct 26, 2026Updated 3 weeks ago
Alternatives and similar repositories for turing-unlock
Users that are interested in turing-unlock are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 2080ti TU102 doing the unlock trick☆150Oct 22, 2026Updated 3 weeks ago
- High-performance Triton backend for NVIDIA Turing (SM75) GPUs.☆54Sep 27, 2026Updated last month
- Chat with any local and remote LLM endpoint and track speed☆18Nov 8, 2026Updated last week
- GPU tensor unlock source for RTX 4090 and experimental RTX 4070 Ti SUPER; firmware generated locally☆4,928Oct 26, 2026Updated 3 weeks ago
- Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput☆20,169Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- GPU Unlock — NVIDIA SM speed-select override kernel module. Merges gpu-unlock-ada (AD102/AD103) and gpu-unlock (GA10x + resume). Docs: ht…☆36Oct 27, 2026Updated 3 weeks ago
- The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-reques…☆1,230Oct 1, 2026Updated last month
- UEFI pre-driver NVIDIA GPU unlocker for Windows Linux Hackintosh and all EFI-bootable system (Rust): SEC2 scrubber -> FWSEC/WPR2 -> signe…☆2,617Updated this week
- ☆87Oct 31, 2026Updated 2 weeks ago
- Inference engine for large language models on consumer GPUs, with deep optimization for older hardware☆55Oct 20, 2026Updated 3 weeks ago
- Reproducible vLLM deployment for Qwen3.8-27B on dual RTX 2080 Ti 22GB with NVLink☆22Sep 7, 2026Updated 2 months ago
- A mini tunnel to a mini computer for ChatGPT.☆14Sep 8, 2026Updated 2 months ago
- MiniMax H3 video generation on 2080Ti 22G (Turing sm_75) - field-tested handbook, workflows & FAQ☆27Nov 9, 2026Updated last week
- Strata v0.1.42 tuning for 2x RTX 2080 Ti 22G (Qwen3.8-Flash-Next Swift IQ3_XXS): 60K/128K prefill 2116/2163 tok/s on 48GB RAM☆15Oct 14, 2026Updated last month
- 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.
- Experimental NVIDIA tensor-compute unlock research: guarded TU102 initramfs port, offline tests, and Ampere reproduction notes☆408Nov 1, 2026Updated 2 weeks ago
- Windows GPU UNLOCK: RTX3090 UEFI port, Korean no-reset Windows boot guide, verified source and benchmark evidence☆2,274Updated this week
- some experiments about 170hx 10g version.☆14Oct 19, 2026Updated 3 weeks ago
- ☆35Oct 20, 2026Updated 3 weeks ago
- 这是一套 MiniMax H3 本地部署与性能优化整理:在 4 张 22 GB RTX 2080 Ti 上,通过 Raylight FSDP/USP、双组NVLink、多卡 Qwen 文本编码节点、SM75 SageAttention 和通信流水,让MiniMax H3 的…☆27Aug 12, 2026Updated 3 months ago
- 掌中有话 · 手相指南:发一张手掌照片,生成直白的娱乐向手相指南 HTML(签、指数、流年流月、掌上年龄尺),适用于 Codex / Claude Code 的 Agent Skill☆34Nov 3, 2026Updated 2 weeks ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆45,204Updated this week
- Fast, local, OpenAI-compatible TTS server with voice cloning support powered by Kyutai's Pocket TTS☆19Oct 13, 2026Updated last month
- Import SillyTavern V2 character cards as SOUL.md personas for SOUL-aware agent runtimes (Hermes-Agent, OpenClaw, …).☆19May 11, 2026Updated 6 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.
- ComfyUI custom nodes and workflow templates for HyperFlow H3 Flash GGUF checkpoints☆97Nov 11, 2026Updated last week
- ☆114Updated this week
- Fast fork of llama.cpp designed for Qwen3.8-Flash-Next☆455Updated this week
- Try to export the ONNX QDQ model that conforms to the AXERA NPU quantization specification. Currently, only w8a8 is supported.☆11Sep 10, 2024Updated 2 years ago
- ☆13Oct 14, 2026Updated last month
- Apply LUTs to RAW photos right in your browser☆14Nov 5, 2026Updated last week
- CPU usage bar widget and iStat-inspired system panel for Omarchy☆14Aug 29, 2026Updated 2 months ago
- ☆20Oct 6, 2021Updated 5 years ago
- Lossless compression of BF16 models to 12-bits☆32Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-the…☆193Nov 9, 2026Updated last week
- Single-file, dependency-free live dashboard for local llama.cpp/vLLM serving — GPU, throughput, KV/ctx, model library. Stdlib Python + on…☆75Nov 3, 2026Updated 2 weeks ago
- ☆15Apr 13, 2026Updated 7 months ago
- 阿里云香港抢占式实例 + CDT 200G 免费流量 + 自动启停:脚本与 SOP☆19Oct 17, 2026Updated last month
- A browser-based UI for launching, monitoring, clustering and managing multiple llama.cpp server instances from inside a Docker container.…☆15Updated this week
- Telegram bot for monitoring Hyperliquid whale trades☆16Sep 20, 2025Updated last year
- llama.cpp fork for two V100 32GB cards to run Qwen3.8FlashNext☆14Nov 3, 2026Updated 2 weeks ago
Are these results useful?