mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
ROCm: - layers.rs: on-device HIP rope dispatch (rocm_rope_positions_qk) + per-token positions expansion in the gather fallback - utils/mod.rs: exclude ROCm from paged_attn_supported() (HIP PagedAttention v1 kernel hangs at runtime on gfx1151) so ROCm defaults to working non-paged attn Plus this session's native-stack tree changes (quant fast_mmq/mmvq, gemv, moe, diffusion/speech/multimodal, zen3-serving, dub e2e tests). ROCm GGUF Q8_0 on gfx1151: ~112 tok/s decode, ~96x CPU. Co-authored-by: Hanzo Dev <[email protected]>