beehive-lab/jllm

port-model-to-jllm

Port a new model architecture to jllm. Use when a GGUF file is not recognized, when a family needs its own program description or lowering, or when deciding whether an existing family's implementation can be reused for a new one.

Langue du texte source : anglais

build-n-run-engine

Build jllm with Maven and run it on an accelerator. Use when target/ is missing or stale, after pulling changes, or when switching JDK line or backend.

Langue du texte source : anglais

update-quarkus-langchain4j-integration

Update the Quarkus LangChain4j jllm extension to a new jllm release. Use when bumping io.github.beehive-lab:jllm in quarkus-langchain4j, adapting the runtime/deployment modules to API or capability changes, validating JDK/TornadoVM combinations and demos, or…

Langue du texte source : anglais

build-tornado

Build a TornadoVM SDK for jllm. Use when TORNADOVM_HOME is unset, points at the wrong JDK line or backend, or the pinned version has moved.

Langue du texte source : anglais

jllm-ncu-analysis

Nsight Compute workflow for one jllm CUDA kernel. Use after nsys, the TornadoVM profiler or the metrics output has already named the hot kernel.

Langue du texte source : anglais

jllm-nsys-analysis

Nsight Systems workflow for jllm on the CUDA backend. Use to capture a timeline and decide where the time goes: generated kernels, launch overhead, synchronization, host-device transfers, or GPU idle.

Langue du texte source : anglais

update-langchain4j-integration

Update the LangChain4j jllm integration to a new jllm release. Use when bumping io.github.beehive-lab:jllm, adapting the adapter to API or capability changes, enabling inherited integration tests, validating JDK/TornadoVM combinations and demos, or updating…

Langue du texte source : anglais