ggml-cuda
PulseAugur coverage of ggml-cuda — every cluster mentioning ggml-cuda across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
llama.cpp releases pre-versions with optimizations and bug fixes · 10 sources tracked
The llama.cpp project has released several pre-release versions, including b12255, b12254, b12253, b12252, b12250, b12249, b12247, b12248, b12246, and b12243. These updates address various issues and introduce improveme…
-
llama.cpp b12151 release updates ggml-cuda for MoE selection
The llama.cpp project released version b12151, which includes an update to ggml-cuda to sanitize post-bias NaNs in MoE selection. This release addresses an issue related to Mixture of Experts (MoE) selection within the …
-
Hugging Face releases Granite Switch 4.1.1 with faster model updates · 2 sources tracked
Hugging Face has released Granite Switch 4.1.1, a patch update to its modular language model architecture. This update includes an improved multilingual Granite Speech ASR model with native punctuation and capitalizatio…
-
llama.cpp updates ggml-cuda, Anthropic SDK releases new features · 2 sources tracked
The llama.cpp project has released version b11770, which includes support for ssm_conv kernel size 7 in ggml-cuda. This update brings compatibility for various platforms including macOS on Apple Silicon and Intel, iOS, …
-
llama.cpp ggml-cuda PR boosts Qwen 3.x prompt processing speed
A pull request to the llama.cpp project, specifically targeting ggml-cuda, introduces an optimization that assigns four GDN state columns per warp. This change aims to improve the speed of Qwen 3.x models, particularly …
-
llama.cpp adds AMD RDNA2 performance improvements · 1 source tracked
A pull request to the llama.cpp project, specifically for ggml-cuda, introduces performance improvements for AMD's RDNA2 architecture, including MI50 and MI60 GPUs. These enhancements are detailed in benchmarks and disc…
-
llama.cpp releases updates with performance and stability fixes · 9 sources tracked
The llama.cpp project has released several updates, including version 0.4.1, which addresses various performance and stability issues across different platforms. Notable changes include optimizations for SYCL backends, …
-
llama.cpp releases multiple updates with performance and bug fixes
The llama.cpp project has released several updates, including versions b9975, b9974, b9973, b9972, b9971, b9970, b9969, b9968, b9966, and b9965. These releases introduce various improvements and bug fixes across multipl…