Models & Labs
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA
Hugging Face Bloghigh confidence
Why it matters
- →LoRA and DoRA enable efficient fine-tuning on a single GPU, reducing costs and memory usage.
- →Synthetic trajectory generation offers a scalable alternative to expensive real-robot data collection.
- →This approach prevents catastrophic forgetting, maintaining the model's general knowledge.
NVIDIA Cosmos Predict 2.5, a large-scale world model, is being fine-tuned using LoRA and DoRA techniques to generate synthetic robot trajectories. This method allows for efficient fine-tuning on a single GPU, reducing memory requirements and preventing the loss of general knowledge. By using small trainable adapter modules, developers can adapt the model to specific domains like robot manipulation. This advancement offers a scalable alternative to collecting real-robot data, potentially accelerating progress in robot learning tasks.
Read originalMore in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.