mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-25 09:09:07 -04:00
6f0792c3be
Mirror of the llama-paged-dev patch 0019 engine change plus the measured
results. Step 2 of the SSM decode work: after Step 1 (in-place state write-back,
patch 0018) the largest non-GEMM decode bucket was the recurrent-state get_rows
gather (18.8 percent of decode GPU time). This removes that materialization,
mirroring ggml_ssm_scan's ids source: ggml_gated_delta_net_inplace_ids reads each
sequence's prior state directly from cache[ids[seq]] (src[5] = full cache,
src[7] = ids), so combined with Step 1's in-place write the op reads AND writes
the cache directly with no state materialization at all.
Race-free by construction: identity sequences (ids[seq] == rs_head + seq, the
whole AR decode path) read s0 in place from the destination slot; non-identity
sequences (reorder / rs_zero, e.g. multi-new-seq prefill) read from a disjoint
scratch a small gather kernel populates first. ids stays a device pointer.
Bit-identical to the get_rows path. Gated to qwen35 + qwen35moe; qwen3next,
kimi-linear, the non-fused and rollback paths are unchanged.
Measured (decode_agg S_TG, npp128 ntg128, -fa on, paged on, fusion off):
q36-27b-nvfp4 dense: npl32 137.64 -> 170.68 (+24.0 percent),
npl128 186.25 -> 256.57 (+37.8 percent, 47.6 -> 65.6 percent of vLLM 391).
q36-35b-a3b-nvfp4 MoE: npl32 299.68 -> 366.69 (+22.4 percent),
npl128 409.30 -> 553.63 (+35.3 percent).
Greedy (--temp 0 --seed 1) llama-completion bit-identical vs the Step-1 build
(dense + MoE). nsys k_get_rows_float bucket 18.8 -> 0.7 percent. The residual
decode gap to vLLM is now the FP4 GEMM (~48 percent of decode). See
SSM_DECODE_FIX_RESULTS.md.
Assisted-by: Claude:opus-4.8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>