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:
- Optimized VLLM for Ampere☆24Oct 18, 2026Updated 2 weeks ago
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,466Updated this week
- an experimental quantized training library☆15Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,177Updated this week
- 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 3 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.
- Local LLM speed measurements from a 4x RTX 3090 rig, with exact launch commands and per-run provenance.☆18Aug 15, 2026Updated 2 months ago
- Experimental llama.cpp fork for inference research and development☆896Updated 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
- 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 5 months ago
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆282Updated this week
- Unlock P2P comms between consumer NVIDIA GPUs☆684Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,772Updated this week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,967Updated this 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.
- PCIe P2P on consumer RTX 5090 via one GSP firmware registry key — no driver patches.☆20Apr 17, 2026Updated 6 months ago
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆82Sep 19, 2026Updated last month
- NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Q…☆27Apr 27, 2026Updated 6 months 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
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆486Updated this week
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆28Jan 30, 2026Updated 9 months ago
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆561Updated this week
- CompChomper is a framework for measuring how LLMs perform at code completion.☆21Apr 29, 2025Updated last year
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆20Oct 16, 2026Updated 2 weeks ago
- 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.
- ☆25Oct 20, 2026Updated last week
- An OpenAI API compatible FastAPI server that sits on top of the Anemll repo. Tested with Open WebUI.☆21Jan 21, 2026Updated 9 months ago
- Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.☆57Apr 5, 2026Updated 6 months ago
- LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features …☆474Sep 22, 2026Updated last month
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆49Updated this week
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆38Sep 25, 2026Updated last month
- ☆342May 15, 2026Updated 5 months ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆268Oct 6, 2026Updated 3 weeks ago
- Unlocking NVIDIA CMP 90HX (GA102): kernel 6.12☆44Aug 22, 2026Updated 2 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.
- DeepSeek-V4-Flash on Ampere SM 8.6 via vLLM (pyref kernel replacements)☆35Jul 2, 2026Updated 3 months ago
- ☆18Jan 3, 2026Updated 9 months ago
- ☆12Aug 31, 2026Updated 2 months ago
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,223Updated this week
- ☆18Jul 1, 2025Updated last year
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆482Oct 14, 2026Updated 2 weeks ago
- vLLM Qwen3.5-122B NVFP4 on DGX Spark (SM121) — full Docker build with 15 patches☆17Mar 17, 2026Updated 7 months ago