Assault-Consulting/Palimpsests

docs: dead-link and typo sweep across docs/ about 1 hour ago

good first issue

0

Layered local-LLM inference engine for agentic workloads: Ollama and llama.cpp behind one abstraction, context-memory (sink/window/evict + block retrieval), encrypted audit log. Native L3 serving layer in progress.

Python

#llama-cpp#llm#llm-inference#local-llm

docs: worked header-only verification example in USAGE.md about 2 hours ago

good first issue

Assault-Consulting/Palimpsests

0

Layered local-LLM inference engine for agentic workloads: Ollama and llama.cpp behind one abstraction, context-memory (sink/window/evict + block retrieval), encrypted audit log. Native L3 serving layer in progress.

Python

#llama-cpp#llm#llm-inference#local-llm

cli: pala --version prints package + spec/profile versions about 2 hours ago

good first issue

Assault-Consulting/Palimpsests

0

Layered local-LLM inference engine for agentic workloads: Ollama and llama.cpp behind one abstraction, context-memory (sink/window/evict + block retrieval), encrypted audit log. Native L3 serving layer in progress.

Python

#llama-cpp#llm#llm-inference#local-llm

cli: pala verify --json machine-readable verdict about 2 hours ago

good first issue

Assault-Consulting/Palimpsests

0

Layered local-LLM inference engine for agentic workloads: Ollama and llama.cpp behind one abstraction, context-memory (sink/window/evict + block retrieval), encrypted audit log. Native L3 serving layer in progress.

Python

#llama-cpp#llm#llm-inference#local-llm

tests: edge-case vectors — empty log and single-record log about 2 hours ago

good first issue

Assault-Consulting/Palimpsests

0

Layered local-LLM inference engine for agentic workloads: Ollama and llama.cpp behind one abstraction, context-memory (sink/window/evict + block retrieval), encrypted audit log. Native L3 serving layer in progress.

Python

#llama-cpp#llm#llm-inference#local-llm

export: --from-seq / --to-seq range flags for the JSONL export about 2 hours ago

good first issue

Assault-Consulting/Palimpsests

0

Layered local-LLM inference engine for agentic workloads: Ollama and llama.cpp behind one abstraction, context-memory (sink/window/evict + block retrieval), encrypted audit log. Native L3 serving layer in progress.

Python

#llama-cpp#llm#llm-inference#local-llm

Open Issues Need Help