https://pypi.org/project/oomllama/ Recent updates to the Python Package Index for oomllama en https://pypi.org/project/oomllama/1.0.0a2/ Sovereign AI Inference Engine — .oom quantization, Trust Kernel encryption, JIS identity routing, TIBET provenance. Spaceshuttle lazy loading, RAM-RAID distributed memory. ai@humotica.nl, jasper@humotica.nl Sun, 19 Apr 2026 17:04:12 GMT https://pypi.org/project/oomllama/1.0.0a1/ Sovereign AI Inference Engine — .oom quantization, Trust Kernel encryption, JIS identity routing, TIBET provenance. Spaceshuttle lazy loading, RAM-RAID distributed memory. ai@humotica.nl, jasper@humotica.nl Sun, 19 Apr 2026 07:11:44 GMT https://pypi.org/project/oomllama/0.9.0/ Efficient LLM inference engine with .oom format - from-scratch Rust, SafeTensors/GGUF converters ai@humotica.nl, jasper@humotica.com Mon, 16 Mar 2026 10:28:26 GMT https://pypi.org/project/oomllama/0.8.0/ Efficient LLM inference engine with .oom format - from-scratch Rust, SafeTensors/GGUF converters ai@humotica.nl, jasper@humotica.com Thu, 26 Feb 2026 15:37:43 GMT https://pypi.org/project/oomllama/0.7.0/ Efficient LLM inference with .oom format - 2x smaller than GGUF ai@humotica.nl, jasper@humotica.nl Wed, 25 Feb 2026 10:45:40 GMT https://pypi.org/project/oomllama/0.6.0/ Efficient LLM inference with .oom format - 2x smaller than GGUF ai@humotica.nl, jasper@humotica.com Sat, 21 Feb 2026 17:08:23 GMT https://pypi.org/project/oomllama/0.5.0/ OomLlama - Smart LLM routing with TIBET provenance. Route queries to the right model, track everything. jasper@humotica.com, info@humotica.com Fri, 20 Feb 2026 13:49:02 GMT https://pypi.org/project/oomllama/0.4.0/ Efficient LLM inference with .oom format - 2x smaller than GGUF. Dual GPU support, RoPE, KV-Cache & Flash Attention! pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Mon, 02 Feb 2026 04:48:34 GMT https://pypi.org/project/oomllama/0.3.7/ Efficient LLM inference with .oom format - 2x smaller than GGUF. Dual GPU support, RoPE, KV-Cache & Flash Attention! pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 22:00:44 GMT https://pypi.org/project/oomllama/0.3.6/ Efficient LLM inference with .oom format - 2x smaller than GGUF. Dual GPU support, RoPE, KV-Cache & Flash Attention! pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 21:33:05 GMT https://pypi.org/project/oomllama/0.3.5/ Efficient LLM inference with .oom format - 2x smaller than GGUF. Dual GPU support, RoPE, KV-Cache & Flash Attention! pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 10:25:55 GMT https://pypi.org/project/oomllama/0.3.4/ Efficient LLM inference with .oom format - 2x smaller than GGUF. Now with RoPE, KV-Cache & Flash Attention! pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 09:33:06 GMT https://pypi.org/project/oomllama/0.3.2/ Efficient LLM inference with .oom format - 2x smaller than GGUF. GPU inference requires: pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 07:35:59 GMT https://pypi.org/project/oomllama/0.3.1/ Efficient LLM inference with .oom format - 2x smaller than GGUF. GPU inference requires: pip install oomllama[cuda] ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 07:32:40 GMT https://pypi.org/project/oomllama/0.3.0/ Efficient LLM inference with .oom format - 2x smaller than GGUF ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 07:25:28 GMT https://pypi.org/project/oomllama/0.2.0/ Efficient LLM inference with .oom format - 2x smaller than GGUF ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 06:14:54 GMT https://pypi.org/project/oomllama/0.1.0/ Efficient LLM inference with .oom format - 2x smaller than GGUF ai@humotica.nl, jasper@humotica.nl Sat, 17 Jan 2026 05:39:08 GMT