SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.
☆133Sep 30, 2026Updated last month
Alternatives and similar repositories for sndr_core_engine
Users that are interested in sndr_core_engine are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,507Updated this week
- Optimized VLLM for Ampere☆24Oct 18, 2026Updated last month
- Validated recipe for serving Qwen3.6-27B on a single RTX 5090 — full OpenAI API, vision, tool calling, MTP spec-decode☆74Apr 29, 2026Updated 6 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,199Updated this week
- Fast open-source (MIT) LLM inference engine in C++/CUDA for RTX 3090-class GPUs: Qwen3.8-Flash-Next (~1,000 tok/s with 8 agents on 3x RTX…☆75Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆28Jul 8, 2026Updated 4 months ago
- an experimental quantized training library☆15Updated this week
- Reproducible llama.cpp configs + per-category quality benches for Qwen3.6-27B on a single RTX 4090. Winners, dead ends, and the silent-co…☆24Apr 26, 2026Updated 6 months ago
- FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with r…☆19Apr 22, 2026Updated 6 months ago
- Experimental llama.cpp fork for inference research and development☆910Nov 13, 2026Updated last week
- vLLM Docker Container for the latest Qwen 27b☆53Sep 27, 2026Updated last month
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆284Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,846Updated this 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.
- Lucebox inference engine for heterogeneous hardware & consumer GPUs☆3,023Updated this week
- 🦙 Docker template for running llama.cpp llama-server in router mode with NVIDIA CUDA and AMD Vulkan GPU acceleration. Features TurboQuan…☆11Jun 25, 2026Updated 4 months ago
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆28Jan 30, 2026Updated 9 months ago
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆523Oct 31, 2026Updated 2 weeks ago
- NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Q…☆29Apr 27, 2026Updated 6 months ago
- Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and …☆580Updated this week
- LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features …☆476Nov 6, 2026Updated 2 weeks ago
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆58Apr 28, 2026Updated 6 months ago
- vLLM 0.33 fork for consumer GPUs: 3 x 262K sessions on Ampere,Ada and more! Qwen 3.8 Flash-Next at 207 tok/s, up to 17 on bigger cards. S…☆51Nov 12, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.☆58Apr 5, 2026Updated 7 months ago
- Local LLM speed measurements from a 4x RTX 3090 rig, with exact launch commands and per-run provenance.☆20Aug 15, 2026Updated 3 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
- llama.cpp fork with additional SOTA quants and improved performance☆3,408Updated this week
- ☆342May 15, 2026Updated 6 months ago
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆53Nov 8, 2026Updated last week
- P2P support for nvidia consumer cards☆26Nov 10, 2026Updated last week
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,771Nov 10, 2026Updated last week
- Production-speed compact Dynamic Memory Sparsification (DMS) for KV cache compression☆27Oct 27, 2026Updated 3 weeks 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.
- ☆18Jan 3, 2026Updated 10 months ago
- PCIe P2P on consumer RTX 5090 via one GSP firmware registry key — no driver patches.☆26Apr 17, 2026Updated 7 months ago
- MiniMax-M3 (MXFP4, MSA) serving on SM120 (RTX PRO 6000 Blackwell) — patched vLLM image + launch recipe, 192K context☆23Jun 15, 2026Updated 5 months ago
- vLLM Qwen3.5-122B NVFP4 on DGX Spark (SM121) — full Docker build with 15 patches☆17Mar 17, 2026Updated 8 months ago
- Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.☆15Nov 14, 2026Updated last week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,387Updated this week
- The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.☆10Jul 7, 2026Updated 4 months ago
Are these results useful?