DaggerSlicer34/koboldcpp
KoboldCpp — local llm cpu.
GitHub repository with 21 stars and 0 forks.
Topics: cpu-inference, gguf, koboldcpp, local-llm, open-source, text-generation
KoboldCpp — local llm cpu.
GitHub repository with 21 stars and 0 forks.
Topics: cpu-inference, gguf, koboldcpp, local-llm, open-source, text-generation
Trending score 1.20, freshness score 0.04, stars gained +13, forks gained +0.
2026-06-02: 21 stars and 0 forks.
KoboldCpp — local llm cpu.
GitHub repository with 21 stars and 0 forks.
Trending score: 1.20; stars gained: +13; forks gained: +0.
Topics: cpu-inference, gguf, koboldcpp, local-llm, open-source, text-generation
Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command
GitHub repository with 20 stars and 1 forks.
Trending score: 0.84; stars gained: +1; forks gained: +0.
Language: Python
Topics: cli, cpu-inference, eli5, fact-checking, llama-cpp, llm
Non-bijunctive attention collapse for LLM inference — POWER8 hardware AES (vcipher) + AltiVec vec_perm. Hebbian path selection, cross-head diffusion, O(1) KV prefiltering.
GitHub repository with 34 stars and 4 forks.
Trending score: 0.10; stars gained: +0; forks gained: +1.
Language: C
Topics: aes, altivec, attention-mechanism, cpu-inference, deep-learning, hardware-acceleration
Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.
GitHub repository with 20 stars and 7 forks.
Trending score: 0.08; stars gained: +0; forks gained: +0.
Language: C
Topics: c, cpu-inference, gguf, inference, llm, quantization
KoboldCpp — local llm cpu.
GitHub repository with 21 stars and 0 forks.
Trending score: 1.20; stars gained: +13; forks gained: +0.
Topics: cpu-inference, gguf, koboldcpp, local-llm, open-source, text-generation
Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command
GitHub repository with 20 stars and 1 forks.
Trending score: 0.84; stars gained: +1; forks gained: +0.
Language: Python
Topics: cli, cpu-inference, eli5, fact-checking, llama-cpp, llm
Non-bijunctive attention collapse for LLM inference — POWER8 hardware AES (vcipher) + AltiVec vec_perm. Hebbian path selection, cross-head diffusion, O(1) KV prefiltering.
GitHub repository with 34 stars and 4 forks.
Trending score: 0.10; stars gained: +0; forks gained: +1.
Language: C
Topics: aes, altivec, attention-mechanism, cpu-inference, deep-learning, hardware-acceleration
Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.
GitHub repository with 20 stars and 7 forks.
Trending score: 0.08; stars gained: +0; forks gained: +0.
Language: C
Topics: c, cpu-inference, gguf, inference, llm, quantization