NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.
☆28Apr 27, 2026Updated 6 months ago
Alternatives and similar repositories for blackwell-geforce-nvfp4-gemm
Users that are interested in blackwell-geforce-nvfp4-gemm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Three-DGX-Spark TP3 serving recipe for GLM-5.3 Flash☆21Oct 5, 2026Updated last month
- High-performance Qwen3.6-35B-A3B-DFlash inference on NVIDIA DGX Spark (~50 tok/s)☆13Apr 20, 2026Updated 6 months ago
- DeepSeek 1017 EXL3 on 3-4 DGX Sparks. TP4 4.0.4: 4,277 tok/s cold prefill; C16 code 331.7 / prose 287.5 native decode sum. Smart CUDA Gra…☆20Nov 4, 2026Updated last week
- ☆14Apr 24, 2026Updated 6 months ago
- Make FP4 on 5090 Great Again☆24Jul 20, 2026Updated 3 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.
- ☆21Aug 6, 2026Updated 3 months ago
- A Comprehensive Benchmark Framework for Retrieval-Augmented Generation (RAG) Routing and Query-Corpus Compatibility.☆14Feb 3, 2026Updated 9 months ago
- llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived f…☆35Updated this week
- 3D fractal renderer written in TypeScript☆11Nov 18, 2024Updated last year
- Index / recipe book for every GLM-5.3 (and GLM-5.2 foundation) serving recipe on NVIDIA DGX Spark (GB10): Flash + big 743B, TP2 + TP4, ev…☆14Aug 29, 2026Updated 2 months ago
- ☆11Updated this week
- A plugin that adds a 3D transition to OBS☆10Aug 3, 2024Updated 2 years ago
- ☆14May 4, 2026Updated 6 months ago
- MachGen's VC attention (https://arxiv.org/html/2609.15810v1) implementation. 2x faster (compared to 1.47-1.6x in original paper) FP8 atte…☆16Oct 12, 2026Updated last month
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated 2 years ago
- Doc Thinker: All-in-One RAG - document parsing, graph RAG, and evaluation☆33Oct 21, 2026Updated 3 weeks ago
- ☆12Feb 10, 2025Updated last year
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Sep 30, 2026Updated last month
- ☆21Oct 31, 2026Updated 2 weeks ago
- Routing-aware expert paging for memory-constrained MoE serving — a vLLM plug-in with byte-identical outputs and joint expert/KV memory al…☆15Sep 15, 2026Updated last month
- ☆19Jan 4, 2024Updated 2 years ago
- Expert Specialization MoE Solution based on CUTLASS☆27Apr 14, 2026Updated 7 months ago
- 👤 Registration and profile management for symfony☆12Oct 30, 2026Updated 2 weeks ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆269Oct 6, 2026Updated last month
- [ACL 2026] WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora☆21May 11, 2026Updated 6 months ago
- The Entity-First TypeScript Framework. Define your data model once — get a type-safe API, schema, auth, and client automatically☆13Feb 2, 2026Updated 9 months ago
- Scalable URL obfuscator service☆11Feb 14, 2023Updated 3 years ago
- Adds carrier column on Order list☆14Sep 3, 2024Updated 2 years ago
- ☆47Nov 1, 2026Updated last week
- ☆25Jun 2, 2026Updated 5 months ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆11Updated this week
- Text embedding and re-ranking in Rust☆14Aug 5, 2026Updated 3 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.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆47Oct 27, 2026Updated 2 weeks ago
- ☆11Dec 8, 2023Updated 2 years ago
- Lightning-fast domain validator for security research. Multi-threaded scanning, smart verification, clean output for pipelines. Ideal for…☆14Dec 9, 2025Updated 11 months ago
- VirgilAblohGPT is an innovative fashion chatbot powered by ChatGLM, now MPT7B added too.. It engages in fashion-related conversations, pr…☆11Nov 9, 2023Updated 3 years ago
- Automaton SCII Chinese Room Abstract Stack Machine C++ Contiguous Data Driven Agentic App framework, ASCII Data Spec, SCRIPT Spec, and Pu…☆14Updated this week
- experimental R/C car autopilot☆19Feb 15, 2020Updated 6 years ago
- End-to-end formally verified solvers for the inviscid Burgers', isotropic viscous Burgers', and full (anisotropic) viscous Burgers' equat…☆18Sep 9, 2026Updated 2 months ago
Are these results useful?