Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + RotorQuant. Main (master) = Qwen4-Exp build; the Qwen35 SWA hybrid lives on the qwen35 branch. RTX 4090.
☆95Sep 24, 2026Updated 2 weeks ago
Alternatives and similar repositories for llama.cpp-turboq-mtp
Users that are interested in llama.cpp-turboq-mtp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆151Jun 13, 2026Updated 3 months ago
- LLM inference in C/C++☆57Updated this week
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆421Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,151Updated this week
- LLM inference in C/C++☆2,426Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Experimental llama.cpp fork for inference research and development☆887Updated this week
- llama.cpp fork optimized for NVIDIA DGX Spark / GB10 (Blackwell, SM 12.1) — TurboQuant weights + KV, NVFP4, DFlash MTP☆32May 26, 2026Updated 4 months ago
- Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parall…☆144Oct 5, 2026Updated last week
- TurboQuant llama.cpp fork with optimized turbo4 kernels for Gemma 4 D=256/512 heads — lazy K/V, batch decode, warp-cooperative write. 120…☆37Apr 5, 2026Updated 6 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,293Updated this week
- One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.☆231May 14, 2026Updated 4 months ago
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆232Oct 3, 2026Updated last week
- LLM inference in C/C++☆35Aug 24, 2026Updated last month
- NEW ROCmfp4 format for llama.cpp☆159Jun 13, 2026Updated 3 months ago
- 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.
- Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on t…☆28May 8, 2026Updated 5 months ago
- wav2lip-api☆11Mar 16, 2023Updated 3 years ago
- ☆12Feb 19, 2025Updated last year
- Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents. Sub-millisecond queries, token budgeting, deterministi…☆24May 18, 2026Updated 4 months ago
- Experimental LLM inference in C/C++☆39May 15, 2026Updated 4 months ago
- ComfyUI implementation of Long-CLIP, including Flux node: LongCLIPTextEncodeFlux☆57Oct 22, 2024Updated last year
- The complete NUMA-optimized branch of the ktransformers project☆26Nov 3, 2025Updated 11 months ago
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆477Aug 17, 2026Updated last month
- Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which increase speed by up to 1.7x☆252Sep 6, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understandi…☆29Apr 23, 2026Updated 5 months ago
- ☆11Oct 2, 2023Updated 3 years ago
- Testbench for llama.cpp llama-server☆15Aug 20, 2025Updated last year
- 在小爱音箱上获得与豆包近乎一致的端侧实时语音对话体验☆29Feb 26, 2026Updated 7 months ago
- Visualization Library for Python☆27Aug 27, 2019Updated 7 years ago
- ☆19Jun 13, 2026Updated 3 months ago
- A llamacpp wrapper to manage and monitor your llama server instance over a web ui.☆29Jun 16, 2026Updated 3 months ago
- Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity sim…☆28Aug 22, 2026Updated last month
- ☆25Apr 28, 2023Updated 3 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 30…☆55Jul 2, 2026Updated 3 months ago
- AutoMapper website☆14Aug 19, 2020Updated 6 years ago
- Real-time voice conversation system with Sesame CSM, featuring web-based audio visualization and GPU acceleration. Educational implementa…☆17Mar 18, 2025Updated last year
- 一款开源的代码管理工具 - 服务端☆19Oct 20, 2025Updated 11 months ago
- 一个语音识别项目☆51May 13, 2025Updated last year
- Spacy, HAC, pytesseract, easyocr, doctr, mmocr, layoutlm, paddleocr☆22Mar 20, 2024Updated 2 years ago
- A fast, Lua-scriptable AI coding agent for the terminal☆55Updated this week