https://pypi.org/project/gridbook/ Recent updates to the Python Package Index for gridbook en https://pypi.org/project/gridbook/0.3.0/ vLLM plugin for the NVFP4-CB / FP8-CB product-codebook weight formats: 2-6 bit-per-weight LLM quantization served by dedicated CUDA decode and prefill kernels. robert.tand@icloud.com Fri, 31 Jul 2026 17:31:37 GMT https://pypi.org/project/gridbook/0.2.0/ vLLM plugin for the NVFP4-CB / FP8-CB product-codebook weight formats: 2-6 bit-per-weight LLM quantization served by dedicated CUDA decode and prefill kernels. robert.tand@icloud.com Fri, 31 Jul 2026 04:51:26 GMT https://pypi.org/project/gridbook/0.1.1/ vLLM plugin for the NVFP4-CB / FP8-CB product-codebook weight formats: 2-6 bit-per-weight LLM quantization served by dedicated CUDA decode and prefill kernels. robert.tand@icloud.com Tue, 28 Jul 2026 20:24:04 GMT https://pypi.org/project/gridbook/0.1.0/ vLLM plugin for the NVFP4-CB / FP8-CB product-codebook weight formats: 2-6 bit-per-weight LLM quantization served by dedicated CUDA decode and prefill kernels. robert.tand@icloud.com Tue, 28 Jul 2026 19:25:53 GMT https://pypi.org/project/gridbook/0.1.0rc1/ vLLM plugin for the NVFP4-CB / FP8-CB product-codebook weight formats: 2-6 bit-per-weight LLM quantization served by dedicated CUDA decode and prefill kernels. robert.tand@icloud.com Tue, 28 Jul 2026 19:21:25 GMT