DeepSeek-V4-Flash on Ampere SM 8.6 via vLLM (pyref kernel replacements)
☆36Jul 2, 2026Updated 4 months ago
Alternatives and similar repositories for vllm-dsv4-ampere
Users that are interested in vllm-dsv4-ampere are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Dogfooding vLLM backport for older GPUs.☆365Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆38Nov 4, 2026Updated 2 weeks ago
- finetune the chain model based on cvte open source model without traing any GMM for frame alignment☆12Aug 6, 2020Updated 6 years ago
- 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 last year
- Open source code for the GCN training algorithm published in IEEE/IPDPS'19☆11Mar 19, 2022Updated 4 years 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.
- Network on chip based neural network accelerator☆11Mar 25, 2021Updated 5 years ago
- 实现moss int8的finetune和优化源moss项目模型保存问题☆17Jun 1, 2023Updated 3 years ago
- vLLM fork for Tesla V100☆15May 31, 2026Updated 5 months ago
- Implementation of Input Stationary, Weight Stationary and Output Stationary dataflow for given neural network on a tiled architecture☆10Apr 19, 2020Updated 6 years ago
- ☆12Jan 22, 2026Updated 9 months ago
- Generates kid-friendly weather forecasts suitable for display on a large monitor. Uses OpenWeatherMap and a local or hosted LLM.☆18Feb 28, 2026Updated 8 months ago
- Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and SM120 (RTX PRO 6000) with vLLM☆209Updated this week
- Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference☆15Nov 13, 2025Updated last year
- Python script to run noxim (https://github.com/davidepatti/noxim) in a simple and better way☆10Dec 18, 2018Updated 7 years ago
- 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.
- GLM-5.2 on 4x DGX Spark with adaptive MTP K2/K4/K5, FULL CUDA graphs, DCP2, 520K context, and a downloadable ARM64 runtime image.☆13Aug 8, 2026Updated 3 months ago
- Official code for paper "Revisiting Model Interpolation for Efficient Reasoning"☆18Jul 14, 2026Updated 4 months ago
- 哈尔滨工程大学模型机设计☆10Mar 14, 2026Updated 8 months ago
- Code for our paper: "Building A Coding Assistant via Retrieval-Augmented Language Models"☆10Nov 2, 2024Updated 2 years ago
- GlobalPoiner中文医疗文本嵌套与非嵌套医疗文本命名实体识别实验☆15May 7, 2022Updated 4 years ago
- ☆36Oct 20, 2026Updated last month
- AI-based command line tool to quickly generate standardized commit messages.☆10Apr 25, 2026Updated 6 months ago
- llama.cpp fork for two V100 32GB cards to run Qwen3.8FlashNext☆15Nov 3, 2026Updated 2 weeks ago
- Give the DeepSeek Harness (dsh) eyes with any text model + any vision model: a vision proxy for chat image attachments and an analyze_ima…☆12Sep 28, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official Implementation of "Can Large Language Models Understand Preferences in Personalized Recommendation?"☆11Sep 21, 2026Updated last month
- ☆11Mar 1, 2023Updated 3 years ago
- FPGA Development toolset☆20Jun 15, 2017Updated 9 years ago
- CUDA Driver API Calls Interception☆12Apr 15, 2024Updated 2 years ago
- keys-latest: GLM-5.2 QuantTrio INT4/INT8 ablit + DFlash · 4x DGX Spark · k=12 · 128k · seqs=4 · KV 10GiB☆14Aug 17, 2026Updated 3 months ago
- Animation Engine | 动画引擎 | Hi Animation | Hello Animation | WIP☆18Sep 13, 2024Updated 2 years ago
- Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025 https://aclanthology.org/2025.naacl-long.…☆18Jun 1, 2026Updated 5 months ago
- Exact SGLang runtime for GLM-5.3-Flash-NVFP4 on 4x RTX PRO 6000 Blackwell (SM120): flashinfer_cutlass MoE, DSA+KDA attention, NEXTN MTP5,…☆17Aug 27, 2026Updated 2 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆22Oct 21, 2026Updated last month
- 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.
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- ☆23Aug 7, 2023Updated 3 years ago
- ☆22Sep 5, 2020Updated 6 years ago
- An object-oriented operating system focused on isolating processes to improve security, portability & scaling☆15Aug 9, 2023Updated 3 years ago
- Ressys benchmark code repo☆12Dec 5, 2025Updated 11 months ago
- Linux P2P unlock and performance fixes for NVIDIA CMP 170HX☆39Sep 22, 2026Updated last month
- SIGIR 2024, Sequential recommendation, Attribute-Opinions, Fine-grained User and Item Representation.☆13Sep 5, 2024Updated 2 years ago
Are these results useful?