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.
☆125Jul 20, 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…☆1,771Updated this week
- Validated recipe for serving Qwen3.6-27B on a single RTX 5090 — full OpenAI API, vision, tool calling, MTP spec-decode☆68Apr 29, 2026Updated 2 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆797Updated this week
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆20Jul 8, 2026Updated 2 weeks ago
- vLLM Docker Container for Qwen3.6 27b☆51Jun 15, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆24Jan 30, 2026Updated 5 months ago
- Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placem…☆256Updated this week
- ☆16Updated this week
- Fast LLM speculative inference server for consumer hardware.☆2,666Updated this week
- DeepSeek-V4-Flash on Ampere SM 8.6 via vLLM (pyref kernel replacements)☆26Jul 2, 2026Updated 2 weeks ago
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆76Jul 14, 2026Updated last week
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆433Updated this week
- LLAMA Turboquant implementation with CUDA support☆705Updated this week
- CompChomper is a framework for measuring how LLMs perform at code completion.☆21Apr 29, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- An OpenAI API compatible FastAPI server that sits on top of the Anemll repo. Tested with Open WebUI.☆21Jan 21, 2026Updated 6 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,061Updated 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 7 months ago
- Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.☆51Apr 5, 2026Updated 3 months ago
- ☆18Jul 1, 2025Updated last year
- ☆339May 15, 2026Updated 2 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆2,950Updated this week
- Llama.cpp launcher with integrated huggingface☆59Updated this week
- vLLM Qwen3.5-122B NVFP4 on DGX Spark (SM121) — full Docker build with 15 patches☆18Mar 17, 2026Updated 4 months 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.
- Rank any list by any criteria at any scale using LLMs as judges.☆30Updated this week
- Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.☆16Updated this week
- Home-enthusiast's guide to fine-tuning 27B+ LLMs on AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — the patches and tuning to make Linux ma…☆26Jun 9, 2026Updated last month
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆398May 29, 2026Updated last month
- A physics-grounded, cost-aware optimizer for vLLM.☆56Updated this week
- llama-swap + a minimal ollama compatible api☆60May 26, 2026Updated last month
- 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
- AdaLLM is an NVFP4-first inference runtime for Ada Lovelace (RTX 4090) with FP8 KV cache and custom decode kernels. This repo targets NVF…☆135Feb 15, 2026Updated 5 months ago
- An fully autonomous agent that accesses the browser and performs tasks.☆18Apr 25, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- 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…☆19Apr 7, 2026Updated 3 months ago
- 大语言模型工具集☆28Aug 1, 2025Updated 11 months ago
- A simple GPT-3 interface to automate core legal writing tasks☆13Mar 8, 2023Updated 3 years ago
- Qwen3.6-35B-A3B-heretic NVFP4 + DFlash speculative decoding on DGX Spark (GB10/sm_121a). Source-built vLLM image + 7 patches + comprehens…☆128Jun 28, 2026Updated 3 weeks ago
- Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon☆47Mar 31, 2026Updated 3 months ago
- LLM inference in C/C++☆2,164Updated this week
- A simple but instructive implementation of DP, TP, FSDP, FSDP+TP using pytorch distributed primitives☆19Apr 12, 2026Updated 3 months ago