Topic: fix

20 stories found

Thursday, July 30, 2026

releases2 sources⚡ Corroborated48

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

Tuesday, July 28, 2026

releases48

ggml/llama.cpp releases: b10172

ggml-webgpu updates address binding alias issues and overlapping range problems across different architectures, ensuring compatibility and stability. These fixes are crucial for maintaining the project's reliability across various computing environments.

github.com↗