This repo contains the critical chat_template.jinja fix for Qwen3/3.5/3.6 to work smoothly in agentic task.
☆95May 2, 2026Updated 6 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:
- vLLM optimized for AMD☆28Nov 3, 2026Updated last week
- ☆17Sep 6, 2026Updated 2 months ago
- An RDNA4 R9700 AI Pro ComfyUI patch for MiniMax H3 to speed up video generation.☆33Aug 8, 2026Updated 3 months ago
- GLM-5.3-Flash NVFP4 (lab quant) on 2x DGX Spark — TP=2 over RoCE, one .env, compose head/worker, download/start/stop/status/tail-log☆11Sep 8, 2026Updated 2 months ago
- Qwen3.5-122B-A10B on a DGX Spark with DFlash speculative decode. One-shot Docker/vLLM installer. 80+ tok/s!☆59Jun 29, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- OmaSeek: the Omarchy spirit and aesthetic. Now in DeepSeek Harness☆21Oct 31, 2026Updated last week
- 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 2 months ago
- Back up and restore app data on-device with TrollStore.☆12Oct 24, 2026Updated 2 weeks ago
- Ekbasis: an open world model for agents. What an action will do, before it is done.☆18Oct 16, 2026Updated 3 weeks ago
- 🔮 A powerful and stylish Prompt Generator powered by OpenAI and Python. Includes a built-in JSON editor, modular prompt libraries, and f…☆20Jul 12, 2025Updated last year
- asmsense: a small model that names and describes functions in stripped x86-64 binaries. Open dataset, baselines, and LoRA experiments.☆20Nov 5, 2026Updated last week
- LLM inference in C/C++☆29Updated this week
- Unlock P2P comms between consumer NVIDIA GPUs☆723Oct 26, 2026Updated 2 weeks ago
- Validate the usable size of your local LLM cache under pressure☆12Sep 26, 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.
- Docker compose serving stack for DeepSeek v4 Flash DSpark for NVIDIA Spark GB10 system using Aidendle94 image☆33Aug 30, 2026Updated 2 months ago
- Fastest validated sglang recipe for Qwen3.8-27B (AWQ-INT4 + DSpark) on RTX 3090s — 1×/2×/4× GPU presets, image+video, full benchmarks☆64Oct 17, 2026Updated 3 weeks ago
- Compressed KV cache as cross-backend wire format for Metal + CUDA split inference over Thunderbolt 5☆15Apr 14, 2026Updated 6 months ago
- Universal cognitive engine for AI. Features autonomy, self-reflection, and continuous learning via the Nine Questions loop.☆14Jun 13, 2026Updated 5 months ago
- Rust terminal monitor for NVIDIA GPUs, Linux systems, and DGX Spark, with per-process memory views and persistent GPU job history.☆105Updated this week
- Recipe for the fastest 4bit qwen3.8FlashNext☆74Nov 7, 2026Updated last week
- 适配泰安S8030显卡机自动调节系统风扇组件☆13Dec 13, 2024Updated last year
- List of open source serverless frameworks by popularity with a short description from the repositories.☆13Sep 24, 2019Updated 7 years ago
- The open-source platform behind Cubepals: Minecraft servers that sleep when empty and wake the moment a player joins, Java and Bedrock on…☆20Updated this 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.
- 在四卡A100上适配Sglang部署deepseek-v4-flash正式版模型☆15Aug 2, 2026Updated 3 months ago
- MiniMax H3-Base video+audio on two NVIDIA DGX Sparks: vLLM-Omni text-encoder TP2 + Ulysses SP2 across a ConnectX-7 cable, 10 s 1344x768 c…☆15Updated this week
- ☆11Aug 22, 2025Updated last year
- ☆11Aug 3, 2026Updated 3 months ago
- MLTF: Qwen3.8-27B q8c inference for Apple Silicon☆14Oct 8, 2026Updated last month
- GLM-5.3-Flash (EXL3) on 2x NVIDIA DGX Spark - Extended KV cache☆13Sep 8, 2026Updated 2 months ago
- Speculative Decoding Implementations: MTP, EAGLE-3, Medusa-1, PARD, Draft Models, N-gram and Suffix Decoding from scratch☆15May 2, 2026Updated 6 months ago
- ☆16Feb 3, 2026Updated 9 months ago
- StatsPro is a open-source, easily deployable, and privacy friendly alternative to Google Analytics.☆13Aug 4, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆35Feb 6, 2026Updated 9 months ago
- CS319 2025W2 Project☆12Apr 20, 2026Updated 6 months ago
- dsv41-flash-pp5-170hx &pp6 Supports the original (full/unquantized) model. Prefill 7,000 t/s, decode 45-75-125 t/s. dspark. Requires 200 …☆13Updated this week
- Archived fork of antirez/ds4 for GB10 DSpark — continues as Athena: github.com/xangel82/Athena-Engine☆28Oct 30, 2026Updated 2 weeks ago
- ☆19Mar 19, 2026Updated 7 months ago
- Recipe for running vLLM productively on Radeon PRO V620 (Navi 21 / gfx1030) on Linux. Multiple Qwen models supported.☆22Sep 6, 2026Updated 2 months ago
- Pet Containers for Data Scientists☆12Dec 8, 2022Updated 3 years ago
Are these results useful?