https://pypi.org/project/hyperloom-inference-optimizer/ Recent updates to the Python Package Index for hyperloom-inference-optimizer en https://pypi.org/project/hyperloom-inference-optimizer/1.0.0b1/ Inference Optimizer — three-role (Orchestration/Critic/Robustness) autonomous LLM inference optimization runtime for AMD GPU platforms. Kernel optimization is handled by programmatic Python handlers. Wed, 12 Aug 2026 07:12:56 GMT https://pypi.org/project/hyperloom-inference-optimizer/1.0.0a3/ Inference Optimizer — single-mode 4-agent (Orchestration/Kernel/Critic/Robustness) autonomous LLM inference optimization runtime for AMD GPU platforms. Tue, 11 Aug 2026 06:08:47 GMT https://pypi.org/project/hyperloom-inference-optimizer/1.0.0a2/ Inference Optimizer — single-mode 4-agent (Orchestration/Kernel/Critic/Robustness) autonomous LLM inference optimization runtime for AMD GPU platforms. Tue, 11 Aug 2026 06:08:18 GMT https://pypi.org/project/hyperloom-inference-optimizer/1.0.0a1/ Inference Optimizer — single-mode 4-agent (Orchestration/Kernel/Critic/Robustness) autonomous LLM inference optimization runtime for AMD GPU platforms. Tue, 11 Aug 2026 06:05:11 GMT https://pypi.org/project/hyperloom-inference-optimizer/0.0.1/ Placeholder release reserving the distribution name for the ROCm Hyperloom inference optimizer runtime; under development. Wed, 05 Aug 2026 11:38:24 GMT