mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-07 11:40:25 +00:00
Piotr Wilkin (ilintar)
75a48a9055
* cuda: enable topk-moe fusion for 288 experts The topk-moe fusion only accepted power-of-2 expert counts (or the special-cased 576), so models with 288 experts (e.g. Step-3.7-Flash) fell back to the unfused per-layer routing chain: softmax/sigmoid, argsort, get_rows, sum_rows, div, clamp, scale. At batch size 1 that is ~330 extra tiny graph nodes per token. 288 is a multiple of the warp size, so the existing kernel already handles it; this adds the missing template instantiation and accepts 288 in the eligibility check. Measured on gfx1151 with Step-3.7-Flash IQ4_XS (llama-bench, -b 4096 -ub 4096 -fa 1 -dio 1 -ctk q8_0 -ctv q8_0; machine idle, before/after paired so pp4096 stays matched as a load control): test | before | after ----------------+----------------+---------------- pp4096 | 460.99 ± 0.45 | 462.47 ± 0.34 (unchanged) tg128 | 19.10 ± 0.04 | 19.56 ± 0.03 (+2.4%) tg128 @ d30000 | 12.68 ± 0.04 | 12.69 ± 0.03 (unchanged) Prompt processing is unaffected (the fusion only touches decode routing). The decode gain is ~+2.4% at shallow context and fades with depth: by 30k tokens each step is attention-bound over the KV cache, so removing the fixed routing overhead is no longer visible. Assisted-By: Claude Fable 5 <noreply@anthropic.com> * Update tests/test-backend-ops.cpp Co-authored-by: Oliver Simons <osimons@nvidia.com> * Add comment for case 288 in topk-moe.cu --------- Co-authored-by: Oliver Simons <osimons@nvidia.com>