Popular repositories Loading

1. Phicomm-M1-Domoticz-Plugin Phicomm-M1-Domoticz-Plugin Public

   Phicomm M1 plugin for domoticz

   Python 23 18

2. glm53-flash-170hx-pp8 glm53-flash-170hx-pp8 Public

   GLM-5.3-Flash (320B MoE) served with vLLM on 8x CMP 170HX (SM80, 64 GB, PCIe Gen2 x4): pipeline-parallel 8, NVFP4 weights, DFlash2 speculative decoding, 1M context. Patches, launch config and bench…

   Python 9 1

3. thor-u-qwen3.8-27b-edgellm thor-u-qwen3.8-27b-edgellm Public

   Qwen3.8-27B on NVIDIA DRIVE Thor (thor-u) with TensorRT Edge-LLM: all-NVFP4 + quantized tree-MTP speculative decoding, 262k-token chunked prefill, OpenAI-compatible server - benchmarks and deployment

   C++ 6 2

4. vllm-sentinel vllm-sentinel Public

   Production GPU + vLLM observability console with BMC, host and model metrics

   TypeScript 3 2

5. thor-fp8-llm thor-fp8-llm Public

   Forked from isenlink/thor-fp8-llm

   Cuda 1

6. thor-u-nemotron-bolt-74b-edgellm thor-u-nemotron-bolt-74b-edgellm Public

   Nemotron 3.5 Bolt 74B-A9B on NVIDIA DRIVE Thor (thor-u) with TensorRT Edge-LLM: NVFP4 + DFlash/LiLiCorr speculative decoding - benchmarks and deployment

   Python 1