Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

hexagon: flash attention rework (optimizations, accuracy improvements, etc) (#25085)

Browse Source 
* hex-mm: fold mm quant tasks into the main matmul threads

* hex-mm: minor formatting fixes

* hex-mm: cleanup is_quant checks in dma dispatch

* hex-mm: fix dst-spad alignment

* hex-mm: move fp kernels in the hvx-mm-kernels header

* hex-mm: fuse with ADD

* hex-fa: factor out ukernels into separate headers and unify the rest

* hex-fa: move kernel-params compute into the host

* hex-fa: refactor vtcm alloc for consistency

* hex-fa: add support for FA_SELECT

* hex-fa: update tracing insrumentation to cover all functions

* hex-fa: update hvx fallback thresholds to recover t/g regressions

* hex-fa: update tracing instrumentation

* hex-fa: improved tracing with additional events

* hex-fa: optimize mask processing (fastdiv, etc)

* hex-fa: improve mask dma caching

* hmx-fa: change loop order to maximize mask cache hits

* hex-fa: remove over instrumentation

* hex-fa: breakdown QKV prep trace events

* hmx-fa: further mask proc optimizations

* hex-fa: mask broadcast is the common case, optimize for that

* hex-fa: use aligned loads where possible

* hex-fa: update loops to use uint32_t indices

* hmx-fa: fold vtcm init into q prep task

* hex-fa: update rest of the hmx funcs to use uint32_t

* hmx-fa: fold build_d into the main softmax loop

* hmx-fa: start kv dmas earlier

* hmx-fa: start mask dma a bit earlier

* hex-fa: precompute rows per task to avoid divs

* hmx-fa: specialize fa_o_store for f16 and f32

* hmx-fa: prelim support for Sinks

* hmx-fa: keep softmax accumulators in fp32

* hex-fa: add tanh_f16 and exp2_f16 and use that in FA

* hex-fa: use fp16 math in the hvx kernel

* hex-fa: avoid expensive float -> __fp16 cast for slopes and softcap

* hex-fa: replace most vec_exp_f32 with vec_exp2_f16

* hmx-fa: vectorize sinks update

* hex-fa: minor formatting

* hmx-fa: fold softcap loop into the tile load

* hmx-fa: use vectoralias to populate sinks

* hex-fa: remove redudant check

* hex-fa: fix vtcm size compute to use fp32 for accumulators

* hex-mm: fix trailing spaces

* hmx-fa: dont use -inf to init mask to avoid conversion overflows

* hex-fa: no need to explicitly guard -inf in the f16->f32 converter now

* hmx-fa: cleanup fa sinks handling

* hex-mm: fixed src2 stride handling when mm is fused with add

* hex-fa: make lto happy
This commit is contained in:
Max Krasnyansky
2026-07-01 06:59:19 -07:00
committed by GitHub
parent b820cc8e6f
commit 13e673863b
24 changed files with 3777 additions and 3023 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp/hvx-base.h
+1 -12
View File
@@ -134,16 +134,7 @@ static inline HVX_Vector hvx_vec_f32_to_f16_shuff(HVX_Vector v0, HVX_Vector v1)
}
static inline HVX_Vector hvx_vec_f32_to_f16(HVX_Vector v0, HVX_Vector v1) {
HVX_Vector v = Q6_Vh_vdeal_Vh(hvx_vec_f32_to_f16_shuff(v0, v1));
#if __HVX_ARCH__ < 79
// replace NaNs with -INF, older arches produce NaNs for (-INF + 0.0)
const HVX_Vector neg_inf = hvx_vec_splat_f16(-INFINITY);
HVX_VectorPred nan = hvx_vec_is_nan_f16(v);
v = Q6_V_vmux_QVV(nan, neg_inf, v);
#endif
return v;
return Q6_Vh_vdeal_Vh(hvx_vec_f32_to_f16_shuff(v0, v1));
}
#if __HVX_ARCH__ >= 79
@@ -170,8 +161,6 @@ static inline HVX_VectorPair hvx_vec_f16_to_f32(HVX_Vector v) {
}
#endif
static inline HVX_Vector hvx_vec_i16_from_hf_rnd_sat(HVX_Vector vin) {
// This looks complicated.
// Ideally should just be Q6_Vh_equals_Vhf(vin)