This repo contains the critical chat_template.jinja fix for Qwen3/3.5/3.6 to work smoothly in agentic task.
☆97May 2, 2026Updated 5 months ago
Alternatives and similar repositories for vLLM-Qwen3-3.5-3.6-chat-template-fix
Users that are interested in vLLM-Qwen3-3.5-3.6-chat-template-fix are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GLM-5.3-Flash (EXL3 4bpw + DFlash2) on 2x NVIDIA DGX Spark: one-shot installer, 33-74 tok/s c1, 1.3M+ context, vision☆43Sep 2, 2026Updated last month
- Qwen3.5-122B-A10B on a DGX Spark with DFlash speculative decode. One-shot Docker/vLLM installer. 80+ tok/s!☆59Jun 29, 2026Updated 3 months ago
- LLM inference in C/C++☆28Updated this week
- Docker compose serving stack for DeepSeek v4 Flash DSpark for NVIDIA Spark GB10 system using Aidendle94 image☆33Aug 30, 2026Updated last month
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 4 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.
- Run MoE models bigger than your RAM, without the speed cliff☆17Oct 16, 2026Updated last week
- ROCm for gfx803 aka RX 460, RX 470, RX 480, RX 550, RX 560, RX 570, RX 580 and RX 590 with custom patches, kernel fixes, etc☆41Oct 6, 2026Updated 2 weeks ago
- ☆23Oct 14, 2026Updated last week
- Universal cognitive engine for AI. Features autonomy, self-reflection, and continuous learning via the Nine Questions loop.☆14Jun 13, 2026Updated 4 months ago
- Tilt-a-tron: pocket-watch game console on the Waveshare ESP32-S3 1.75in round AMOLED☆38Sep 22, 2026Updated last month
- Single-file, dependency-free live dashboard for local llama.cpp/vLLM serving — GPU, throughput, KV/ctx, model library. Stdlib Python + on…☆76Aug 15, 2026Updated 2 months ago
- The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; bench…☆87Updated this week
- A minimal AI agent that gives an LLM a handful of tools, then gets out of the way.☆12Oct 9, 2026Updated 2 weeks ago
- Starlight is designed to be the hypervisor for everyone!☆13Dec 5, 2025Updated 10 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A database of knowledge around inference & training on GFX906 GPUs https://skyne98.github.io/wiki-gfx906/☆18Feb 21, 2026Updated 8 months ago
- glm-5.2 on too many 64 / 80 GB A100's☆22Sep 9, 2026Updated last month
- Self-contained LTX 2.5 upscaling and MiniMax H3 video refinement nodes for ComfyUI☆18Aug 14, 2026Updated 2 months ago
- ☆14Oct 6, 2026Updated 2 weeks ago
- Maic: A high-performance, MLX-optimized Local LLM server for Apple Silicon. OpenAI-compatible API for M1/M2/M3/M4 Macs and Mac Mini with …☆16Sep 14, 2026Updated last month
- ☆35Feb 6, 2026Updated 8 months ago
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated last month
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆37Sep 28, 2026Updated 3 weeks ago
- An RDNA4 R9700 AI Pro ComfyUI patch for MiniMax H3 to speed up video generation.☆34Aug 8, 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.
- Unlock P2P comms between consumer NVIDIA GPUs☆599Sep 16, 2026Updated last month
- ☆16Feb 3, 2026Updated 8 months ago
- Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.☆136Updated this week
- A tool to create, build, and manage MCP servers for use with Claude and other MCP clients☆12Mar 14, 2025Updated last year
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆104Oct 17, 2026Updated last week
- Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understandi…☆29Apr 23, 2026Updated 6 months ago
- From the world's largest port to the nation's first freeways to pioneering aqueducts, California's history has been defined by visionary …☆13Sep 17, 2026Updated last month
- 🚿 Llaminar: an LLM inferencing engine in C++.☆45Oct 9, 2026Updated 2 weeks ago
- STROT (arXiv:2505.01636): compile-time LLM code synthesis with deterministic, self-routing NLU runtimes. PyPI: strot-ai☆44Updated this week
- 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.
- ik_llama.cpp's Thireus fork with release builds for macOS/Windows/Ubuntu CPU, Vulkan and CUDA☆181Updated this week
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆58Apr 28, 2026Updated 5 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,168Updated this week
- Railyard is a local desktop app for working with Pi across Git repositories and long-running goals. Plan, implement, and pick up where yo…☆25Oct 14, 2026Updated last week
- ☆17May 21, 2026Updated 5 months ago
- Bluetooth Low Energy framework for communicating with Combustion Inc. Predictive Thermometers.☆10Oct 15, 2026Updated last week
- Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, art…☆43Updated this week