SHA-1, SHA-256 and SHA-512 compression functions using Intel, ARMv8 and Power8 SHA intrinsics
-
Updated
Jan 8, 2026 - C
#
power8
Here are 20 public repositories matching this topic...
Sort: Most stars
Sort options
LLM infrastructure cost reduction via NUMA-aware weight banking: 147 t/s (8.8x stock llama.cpp) on refurbished enterprise POWER8. Self-hosted inference, no cloud APIs. Part of the Proof of Physical AI stack.
self-hosted transformer numa powerpc energy-efficiency ppc64le cost-optimization power8 inference-optimization edge-ai hebbian depin ai-inference llm llmops llama-cpp llm-inference ai-infrastructure proof-of-physical-ai vec-perm
-
Updated
Sep 3, 2026 - Python
llama.cpp optimizations for IBM POWER8: vec_perm non-bijunctive collapse, PSE hardware entropy, DCBT prefetch. Sovereign inference. Part of the Proof of Physical AI stack.
transformer ibm powerpc pse ppc64le power8 ai-inference llm llama-cpp llm-inference vintage-computing sovereign-ai vintage-hardware sovereign-inference proof-of-physical-ai vec-perm
-
Updated
Sep 6, 2026 - C
Native ppc64le modules for llama.cpp webui (lightningcss, tailwindcss-oxide) - Built on IBM POWER8
-
Updated
Feb 26, 2026
AES encryption function using Intel, ARMv8 and Power8 intrinsics
-
Updated
Apr 5, 2024 - C
Non-bijunctive attention collapse for LLM inference — POWER8 hardware AES (vcipher) + AltiVec vec_perm. Hebbian path selection, cross-head diffusion, O(1) KV prefiltering.
machine-learning deep-learning aes inference transformer attention-mechanism powerpc hardware-acceleration altivec hebbian-learning power8 cpu-inference llm llama-cpp non-bijunctive
-
Updated
Aug 6, 2026 - C
RPI (Resonant Permutation Inference) — Zero-multiply text generation. 18K tok/s. 868 KB models. Standalone or as speculative draft engine for LLMs. Runs on N64, POWER8, x86, ARM.
mips powerpc nintendo-64 cost-optimization power8 embedded-ai edge-ai tinyml cpu-inference llm llm-inference speculative-decoding
-
Updated
Aug 6, 2026 - C
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Radical LLM cost reduction: no cloud API, no GPU farm. Tiny engine, immense model. 🐦
self-hosted transformer powerpc cost-optimization power8 mixture-of-experts cpu-inference llm llmops local-llm llm-inference sovereign-ai
-
Updated
Jul 13, 2026 - C
Personal blog - debene.dev | Hugo + PaperMod | Self-hosted on K8s via Cloudflare Tunnel
-
Updated
Aug 21, 2026 - HTML
Accelerate LLM inference by collapsing attention paths with hardware-optimized selective pruning using POWER8 vector instructions and crypto operators.
machine-learning deep-learning aes inference transformer attention-mechanism powerpc hardware-acceleration altivec hebbian-learning power8 cpu-inference llm llama-cpp non-bijunctive
-
Updated
Sep 6, 2026 - C
Add this topic to your repo
To associate your repository with the power8 topic, visit your repo's landing page and select "manage topics."