Pinned Repositories
distributed-llama
Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and increase inference speed.
export-nemo-to-safetensors
Simple script to export NeMo formatted models into safetensors.
farel-bench
Testing LLM reasoning abilities with family relationship quizzes.
likwid
Performance monitoring and benchmarking suite
lineage-bench
Testing LLM reasoning abilities with lineage relationship quizzes.
llama-cpp-python
Python bindings for llama.cpp
llama.cpp
LLM inference in C/C++
numaprof
NUMAPROF is a NUMA memory profliler based on Pintool to track your remote memory accesses.
smol-course
A course on aligning smol models.
tlcl
Simple Tool Caller for llama.cpp
fairydreaming's Repositories
fairydreaming/farel-bench
Testing LLM reasoning abilities with family relationship quizzes.
fairydreaming/lineage-bench
Testing LLM reasoning abilities with lineage relationship quizzes.
fairydreaming/llama.cpp
LLM inference in C/C++
fairydreaming/distributed-llama
Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and increase inference speed.
fairydreaming/tlcl
Simple Tool Caller for llama.cpp
fairydreaming/export-nemo-to-safetensors
Simple script to export NeMo formatted models into safetensors.
fairydreaming/likwid
Performance monitoring and benchmarking suite
fairydreaming/llama-cpp-python
Python bindings for llama.cpp
fairydreaming/numaprof
NUMAPROF is a NUMA memory profliler based on Pintool to track your remote memory accesses.
fairydreaming/smol-course
A course on aligning smol models.
fairydreaming/xor-bench
Can LLMs calculate XOR?