vLLM fork for Tesla V100 (SM70) with AWQ 4-bit support, CUDA 12.8 build flow, and validated Qwen3.5 27B/35B deployment on multi-GPU V100.
☆537Jul 20, 2026Updated this week
Alternatives and similar repositories for 1Cat-vLLM
Users that are interested in 1Cat-vLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆19Jun 20, 2026Updated last month
- forked from vllm-project/flash-attention☆57May 9, 2026Updated 2 months ago
- This project is specifically developed for V100, based on lmdeploy 0.12.1, and supports mainstream open-source models from Q4 2025 to Q1 …☆21Mar 18, 2026Updated 4 months ago
- marlin_v100 是一个从 vLLM 主树中提取出来的最小 Marlin 独立开发工作区，聚焦于 Marlin dense 与 Marlin MoE 的源码开发、最小构建和轻量验证。它保留了核心 CUDA/C++ 实现、最小 Python 薄封装、生成器测试与主树回写…☆19Jul 2, 2026Updated 2 weeks ago
- Local LLM Inference Speed Test Tool☆116Jul 2, 2026Updated 2 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.
- vllm混合推理扩展插件，支持多NUMA混合推理，单卡推理Qwen3-Next模型可达1000+ prefill☆34Nov 7, 2025Updated 8 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 …☆386Updated this week
- The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with 100+ tok/s single-request decode…☆429Jul 13, 2026Updated last week
- llama.cpp fork with additional SOTA quants and improved performance☆2,943Updated this week
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆432Feb 20, 2026Updated 5 months ago
- FORK of VLLM for AMD MI25/50/60. A high-throughput and memory-efficient inference and serving engine for LLMs☆71May 4, 2025Updated last year
- Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.☆291Updated this week
- 大语言模型工具集☆28Aug 1, 2025Updated 11 months ago
- Fast LLM speculative inference server for consumer hardware.☆2,668Updated this week
- 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.
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆125Updated this week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆75Jul 14, 2026Updated last week
- Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parall…☆97Updated this week
- Unified KV cache compression for LLM inference — TurboQuant, IsoQuant, PlanarQuant, TriAttention. 10 methods, GPU-validated, multi-GPU pl…☆24Jul 11, 2026Updated last week
- Zoof is a high-efficiency Small Language Model (SLM) engineered from scratch. It demonstrates how modern architectural choices and high-q…☆47Jan 13, 2026Updated 6 months ago
- ☆19Updated this week
- ☆59Dec 9, 2025Updated 7 months ago
- A PyTorch framework for training transformer language models with Mixture of Experts (MoE) architecture support, Mixture of Depths (MoD),…☆21Updated this week
- ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆282Jul 8, 2026Updated last 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.
- Run DeepSeek-V4-Flash on SM89 (Ada / RTX 4090) with vLLM — patch over PR #41834. Validated on 4x RTX 4090.☆20Updated this week
- triton for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆48Dec 8, 2025Updated 7 months ago
- The code implementation of HyGRAG, accepted by WWW'26.☆15May 31, 2026Updated last month
- Give OpenClaw the power to control your desktop — UI-TARS VLM-driven GUI automation☆18Feb 17, 2026Updated 5 months ago
- Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval☆26Mar 3, 2026Updated 4 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆445Apr 17, 2026Updated 3 months ago
- LM inference server implementation based on *.cpp.☆292Nov 24, 2025Updated 7 months ago
- Aggressive decode optimizations for Qwen3-0.6B on RTX 5090☆54Feb 25, 2026Updated 4 months ago
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆31Jul 8, 2026Updated last 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.
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆24Jan 30, 2026Updated 5 months ago
- Claude Code ↔ Codex - Dual-Agent R&D☆16Jul 1, 2026Updated 2 weeks ago
- LLM inference in C/C++☆2,152Updated this week
- The most comprehensive community resource for the NVIDIA CMP 170HX.☆32Jul 13, 2026Updated last week
- vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-strea…☆47May 10, 2026Updated 2 months ago
- 🔍📃 LLM-powered PDF Table Extractor☆19Jun 26, 2025Updated last year
- fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tp…☆4,854Updated this week