b10410 b10408
ggml-org/llama.cppAug 13, 2026 → Aug 13, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10410 and b10408. This page updates automatically — usually within a minute.
The Two Releases
b10410
b10410
Aug 13, 2026· 2 months ago
Refactors the SYCL gemm (General Matrix Multiply) implementation to use automatic fp16 promotion instead of manual type promotion.
Full release notesb10408
b10408
Aug 13, 2026· 2 months ago
Adds support for SYCL ESIMD (Exponential-SIMD) kernels for multiple quantization types, improving performance on Intel GPUs.
Full release notes