exl3

Here are 8 public repositories matching this topic...

samuelcardillo / glm-5.3-flash-2x-rtx-pro-6000-blackwell

Validated GLM-5.3 Flash recipe for 2x NVIDIA RTX PRO 6000 Blackwell 96GB: 262K context, EXL3/TR3, adaptive MTP, tools, and vision.

multimodal long-context vllm local-llm speculative-decoding nvidia-blackwell rtx-pro-6000 exl3 glm-5-3

Updated Aug 28, 2026
Shell

Reederey87 / glm53-flash-exl3-2x-dgx-spark

Star

GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spec decode

self-hosted glm sparse-attention llm-serving vllm llm-inference flashinfer gb10 dgx-spark tensor-parallel exl3

Updated Sep 1, 2026
Python

vcruz305 / GLM-5.3-Flash-EXL3-K2-DGX-Spark-recipe

Star

vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.

glm quantization llm vllm dgx-spark exl3

Updated Aug 31, 2026
Python

ExQ-AI / ExQServe

Star

LLM inference server for ExLlamaV3 / EXL3, with OpenAI- and Anthropic-compatible APIs optimized for Agent workloads.

inference-server ai-agent llm-serving local-llm qwen openai-compatible exllamav3 exl3

Updated Aug 30, 2026
Python

jpanasuk-netizen / tabby-tavern-stack

Star

Containerized private AI lab: TabbyAPI EXL3 + SillyTavern + Open WebUI + Ollama + SearXNG

docker sillytavern local-ai ollama open-webui tabbyapi exl3

Updated Aug 25, 2026
Jinja

brandonmmusic-max / glm52-exl3-sparkinfer

Star

GLM-5.2 753B MoE at EXL3-TR3 3.0bpw on 4x RTX PRO 6000 (SM120): digest-pinned serving stack, validation suite, results. Upstream: vllm#139 / sparkinfer#49

glm quantization blackwell vllm llm-inference speculative-decoding sm120 exl3

Updated Aug 22, 2026
Python

UnsignedChad / glm53-flash-ablit-exl3-2x-dgx-spark

Sponsor

Star

Fail-closed two-DGX-Spark deployment reference for the abliterated GLM-5.3-Flash generic EXL3 4bpw release

vllm dgx-spark glm-5 exl3 glm-5-3 abliterated-model

Updated Aug 29, 2026
Python

samuelcardillo / glm-5.3-flash-uncensored-exl3-2x-rtx-pro-6000-blackwell

Star

Reproducible 262K GLM-5.3 Flash Uncensored EXL3+DFlash2 deployment for 2x RTX PRO 6000 Blackwell

blackwell vllm local-llm rtx-pro-6000 exl3 glm-5-3 dflash2

Updated Aug 31, 2026
Python

Add this topic to your repo

To associate your repository with the exl3 topic, visit your repo's landing page and select "manage topics."

Learn more