-
Notifications
You must be signed in to change notification settings - Fork 273
Pull requests: sonos/tract
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
riscv64: 4 of 4: RVV element-wise and reduction kernels
#2602
opened Aug 7, 2026 by
czoli1976
Contributor
Loading…
riscv64: 3 of 4: 8 and i32 RVV matmul kernels
#2601
opened Aug 7, 2026 by
czoli1976
Contributor
Loading…
riscv64: 2 of 4: 16 RVV matmul kernels behind Zvfh
#2600
opened Aug 7, 2026 by
czoli1976
Contributor
Loading…
riscv64: 1 of 4: RVV 1.0 f32 matmul kernels
#2599
opened Aug 7, 2026 by
czoli1976
Contributor
Loading…
linalg: AVX (no FMA) kernel tier for pre-Haswell x86
#2598
opened Aug 6, 2026 by
czoli1976
Contributor
Loading…
pulse: skip PulsePad's copy and symbol re-resolution on pass-through pulses
#2597
opened Aug 6, 2026 by
czoli1976
Contributor
Loading…
linalg,core: zero the padding lanes the mmm kernels compute on
#2596
opened Aug 6, 2026 by
czoli1976
Contributor
Loading…
linalg/wasm: make the relaxed-dot int8 path bit-exact on all engines
#2594
opened Aug 6, 2026 by
czoli1976
Contributor
Loading…
core/cnn: SIMD-vectorize BlockedConv's inner loop for WASM
#2592
opened Aug 6, 2026 by
czoli1976
Contributor
Loading…
linalg/wasm: fused simd128 f32 kernels for gelu, silu and erf
#2591
opened Aug 6, 2026 by
czoli1976
Contributor
Loading…
reduce: accumulate the generic f16 row sums in f32
#2587
opened Aug 4, 2026 by
czoli1976
Contributor
Loading…
softmax: accumulate the f16 row sum in f32
#2586
opened Aug 4, 2026 by
czoli1976
Contributor
Loading…
tanh: give aarch64 cores without FEAT_FP16 an f32-roundtrip f16 kernel
#2584
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
silu: serve f16 from a table instead of widening every chunk to f32
#2583
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
gelu: saturate the fused f32 kernel's tanh to exactly -1
#2582
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
gelu: fuse the erf-form chain into a single op
#2581
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
rms_norm: run f16 rows natively instead of widening the whole tensor
#2580
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
erf: serve f16 from a table instead of converting the whole tensor each eval
#2579
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
gelu: dispatch f16 through linalg and back it with a lookup table
#2568
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
WASM PR 4: fold the repeated fused-op arms into macros
#2566
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
WASM PR 3: test the invariants the WASM kernels rely on, and run CI against relaxed-simd
#2565
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
WASM PR 2: move the WASM microbenches out of src and into the bench target
#2564
opened Aug 3, 2026 by
czoli1976
Contributor
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.