Popular repositories Loading

1. glm53-flash-cmp170hx-recipe glm53-flash-cmp170hx-recipe Public

   GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 437 tok/s single-user, 841 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install

   Python 56 8

2. vllm-cmp170hx vllm-cmp170hx Public

   Forked from vllm-project/vllm

   vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several

   Python 6

3. cmpunlocker cmpunlocker Public

   Forked from amoghmunikote/cmpunlocker

   A tool to unlobotomize your NVIDIA card!

   Shell 2

4. local-studio local-studio Public

   Forked from sybil-solutions/local-studio

   Control panel for VLLM, Sglang, llama.cpp, exllamav3

   TypeScript

5. oh-my-pi oh-my-pi Public

   Forked from can1357/oh-my-pi

   ⌥ Coding agent with the IDE wired in

   TypeScript

6. local-ai-registry local-ai-registry Public

   Forked from 0xSero/local-ai-registry

   Local AI registry: one validated recipe per machine, with the evidence attached

   HTML