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.
☆132Sep 19, 2026Updated this week
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, llama.cpp, ik_llama) and model-agnostic. Currentl…☆2,278Updated this week
- Validated recipe for serving Qwen3.6-27B on a single RTX 5090 — full OpenAI API, vision, tool calling, MTP spec-decode☆74Apr 29, 2026Updated 4 months ago
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆26Jul 8, 2026Updated 2 months ago
- ☆119Apr 28, 2026Updated 4 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,105Updated this week
- 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.
- 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 4 months 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…☆25Apr 27, 2026Updated 4 months ago
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆275Updated this week
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆58Apr 28, 2026Updated 4 months ago
- ☆20Jul 21, 2026Updated 2 months ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,870Updated this week
- Unlock P2P comms between consumer NVIDIA GPUs☆541Updated this week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆81Updated this week
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆539Updated 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.
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆310Updated this week
- CompChomper is a framework for measuring how LLMs perform at code completion.☆21Apr 29, 2025Updated last year
- Experimental llama.cpp fork for inference research and development☆870Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,472Updated this week
- ☆85Updated 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 …☆461Updated this week
- ☆16Nov 21, 2025Updated 10 months ago
- Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)☆82Updated this week
- This guide is beginner-friendly, project-driven, and laser-focused on the commands & concepts you will actually use while working with Do…☆16Dec 20, 2025Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- llama.cpp fork with additional SOTA quants and improved performance☆3,251Updated this week
- Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.☆56Apr 5, 2026Updated 5 months ago
- ☆18Jul 1, 2025Updated last year
- ☆341May 15, 2026Updated 4 months ago
- Llama.cpp launcher with integrated huggingface☆72Sep 8, 2026Updated last week
- vLLM Qwen3.5-122B NVFP4 on DGX Spark (SM121) — full Docker build with 15 patches☆17Mar 17, 2026Updated 6 months ago
- Rank any list by any criteria at any scale using LLMs as judges.☆29Sep 9, 2026Updated last week
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆474Aug 17, 2026Updated last month
- A physics-grounded, cost-aware optimization loop for vLLM☆67Aug 22, 2026Updated 3 weeks ago
- 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.
- llama-swap + a minimal ollama compatible api☆63Updated this week
- WebAISum is a Python script that allows you to summarize web pages using AI models. It supports both local models like Ollama and remote …☆15Apr 28, 2024Updated 2 years ago
- A database of knowledge around inference & training on GFX906 GPUs https://skyne98.github.io/wiki-gfx906/☆17Feb 21, 2026Updated 7 months ago
- ☆63Aug 6, 2026Updated last month
- 30 tok/s for 20B MoE on 8 GB VRAM. Flat throughput to 32K context. Native MXFP4 + GGUF Q4_K/Q5_K/Q6_K via ggml CUDA kernels — zero dequan…☆22Apr 7, 2026Updated 5 months ago
- The recurrent of KBQA by using Mysql to storage the triple data, using Bert for NER and Sentence Similarity☆13Oct 12, 2019Updated 6 years ago
- A simple GPT-3 interface to automate core legal writing tasks☆13Mar 8, 2023Updated 3 years ago