Topic: ggml

49 stories found

Thursday, July 30, 2026

releases4 sources🛡️ Verified48

ggml/llama.cpp releases: b10199

The ggml/llama.cpp project released version b10199, which adds support for input embedding to generate the next token and fixes issues with server_batch(). These updates enhance the model's functionality and performance.

Covered by ggml/llama.cpp releases

releases48

ggml/llama.cpp releases: b10197

The ggml/llama.cpp project added support for alternative convolution layouts, enhancing flexibility and ensuring compatibility across different computational kernels. This update is crucial for improving the library's versatility in handling various neural network architectures.

github.com↗

Wednesday, July 29, 2026

releases2 sources⚡ Corroborated48

ggml/llama.cpp releases: b10182

The ggml/llama.cpp project released a new version addressing security issues by moving suppress_tokens handling to common/sampling and removing has_logit_bias, emphasizing improved safety in the latest update.

Covered by ggml/llama.cpp releases

releases48

ggml/llama.cpp releases: b10181

The ggml-cuda project updated its code to disable Multi-Memory Queue (MMQ) on devices with less than 48 KiB of shared memory, ensuring optimal performance across different hardware configurations. This update is crucial for maintaining compatibility and efficiency in various computational environments.

github.com↗

Tuesday, July 28, 2026

releases2 sources⚡ Corroborated48

ggml/llama.cpp releases: b10173

The ggml/llama.cpp project has released version b10173, which includes the addition of the Laguna-S-2.1 language model. This update is significant for developers and users interested in advanced text generation capabilities.

Covered by ggml/llama.cpp releases

releases48