vLLM + Qwen3.5-122B-A10B-NVFP4 on NVIDIA DGX Spark (GB10/SM121) — single-GPU NVFP4 W4A4 with MTP speculative decoding, self-contained Docker build
-
Updated
Mar 12, 2026 - Python
#
vllm-server
Here are 11 public repositories matching this topic...
MLOps — vLLM + LiteLLM + Portainer CE + Netdata. Case study song ngữ: kiến trúc, metrics, bài học vận hành. · Self-hosted LLM inference done the MLOps way, a bilingual case study
docker gpu selfhosted self-hosted portainer observability case-study netdata llm case-study-project vllm vllm-production-stack vllm-server
-
Updated
Aug 16, 2026 - HTML
Wheels & Docker images for running vLLM on CPU-only systems, optimized for different CPU instruction sets
-
Updated
Oct 7, 2026 - Shell
A simple UI and config generator to run vLLM with Docker, GPU settings, model config parsing, memory estimation, and OpenAI-compatible test clients.
python docker flask docker-compose cuda flask-application model-serving mlops huggingface llm vllm vllm-ui vllm-serve vllm-server vllm-serving
-
Updated
Oct 18, 2026 - JavaScript
Single-file GPU/RAM sizing calculator for LLM agent sessions on vLLM: KV-cache offload to RAM, prefix caching, MLA/DSA and hybrid models, TP chosen per model × GPU pair (H100–B300). Runs in the browser, no dependencies.
ai ai-agents ai-agent llm ai-calculator vllm llm-agent llm-inference llm-agents sglang deepseek-v3 vllm-server-config vllm-server deepseek-v4 llm-calculator glm-5-3 glm-5-3-flash qwen38-27b qwen38-flash-next
-
Updated
Sep 24, 2026 - HTML
Run GGUF through llama.cpp and SafeTensors through vLLM behind one OpenAI-compatible endpoint. Your coding tools select a model; the switchboard manages the local runtime, process, and resident-model change.
openai llama-cpp vllm local-llm llm-inference llm-serve gguf gguf-models vllm-serve openai-compatible gguf-model-support model-swap llm-service gguf-manager vllm-server model-swapping llm-serving-systems gguf-model gguf-runner models-switcher
-
Updated
Oct 14, 2026 - Rust
Run an AI vision model on Google Colab and use it from your local computer through a public API.
google-colab colab-notebook googlecolab openai-api cloudflare-tunnel vision-language-model ollama multimodal-ai vllm-server run-llm-on-colab free-gpu-ai colab-gpu-api
-
Updated
May 3, 2026 - Python
Multi-agent system for automated mobile QA testing using LLMs, ADB, and vision-grounded execution with Simular Agent S3
-
Updated
Dec 20, 2025 - Python
A simple LLM gateway for routing requests across multiple LLM servers.
-
Updated
Sep 30, 2026 - Rust
Complete self-hosted AI server stack on the Nvidia DGX Spark (arm64)
setup ai nvidia setup-guide setup-script vllm qwen ai-stack vllm-production-stack dgx-spark vllm-server vllm-inference nvidia-dgx-spark
-
Updated
Oct 5, 2026 - HTML
Serves cyankiwi/Qwen3.8-27B-AWQ-INT4 (dense 27B vision-language, reasoning, apache-2.0, ~21GB INT4 weights) via vLLM on a single A100-80GB. via Modal
-
Updated
Sep 6, 2026 - Python
Add this topic to your repo
To associate your repository with the vllm-server topic, visit your repo's landing page and select "manage topics."