4 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Frosty40andGitHub	6703d7894c	sycl: fuse rms_norm+mul+add and add+add residual chains (#27610) ... Fuse RMS_NORM+MUL+ADD and ADD+ADD under GGML_SYCL_ENABLE_FUSION. ADD+ADD uses the same binbcast indexing and type matrix as standalone add() (f32, f16, f16/f32, i32, i16, bf16, including broadcast and non-contiguous). Unsupported combinations fall back to two add() launches.	2026-09-04 00:05:40 -04:00
3 people	91c631b21d	chat : fix reasoning leak with force-opened bare <think> templates (#24674) ... * chat : fix reasoning leak with force-opened bare <think> templates The reasoning start tag inferred from prior turns can carry trailing whitespace (e.g. <think>\n) while a force-open template prefills a bare <think>. Trim the tag used for the prefix split so the bare prefill is matched instead of being swallowed into content. * chat : fix Nemotron Nano v2 regression --------- Co-authored-by: Alde Rojas <hello@alde.dev>	2026-07-13 09:45:10 +02:00
3 people	efb3036c18	sycl: add fused top-k MoE (#25217) ... * sycl: add fused top-k MoE * sycl: address review: GGML_SYCL_ENABLE_FUSION env, move fusion dispatch to topk-moe * sycl: print GGML_SYCL_ENABLE_FUSION at startup like other env vars Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>	2026-07-13 09:56:41 +03:00
Frosty40andGitHub	ac79caa7ce	sycl: support reordered Q4_K/Q5_K/Q6_K MoE MUL_MAT_ID (#24452) ... * sycl: support reordered Q4_K and Q5_K MoE MUL_MAT_ID Extend reordered-weight handling to fused MoE MUL_MAT_ID for Q4_K and Q5_K expert tensors and add Q5_K reordered DMMV coverage. Unsupported 3D reorder cases now fall back instead of aborting. * sycl: extend MoE reorder to Q6_K mul_mat_id	2026-06-16 08:35:00 +03:00