Skip to content

Pull requests: sonos/tract

New pull request New
32 Open 2,346 Closed
32 Open 2,346 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

GatedDeltaNet recurrent and causal-conv1d-update kernels
#2761 opened Sep 1, 2026 by JulienBalianSonos Collaborator Loading…
1
onnx: lower SimplifiedLayerNormalization to RMS norm, not LayerNorm
#2749 opened Aug 30, 2026 by Jorge-Polanco-Roque Loading…
1
3
(perf) core/cnn: vectorise depthwise along contiguous W
#2735 opened Aug 27, 2026 by czoli1976 Contributor Loading…
(perf) core/einsum: do not pick AMX/SME when C's n axis is strided
#2733 opened Aug 27, 2026 by czoli1976 Contributor Loading…
1
(perf) core: fuse a squeezed unit matmul axis and a unicast Mul+Add pair
#2728 opened Aug 26, 2026 by czoli1976 Contributor Loading…
8
(fix)core/cnn: fuse ONNX QDQ Conv into int8 GEMM instead of running it in float
#2725 opened Aug 25, 2026 by czoli1976 Contributor Loading…
(perf) core,onnx: GruSeq: run a GRU as one op instead of a per-timestep scan
#2717 opened Aug 24, 2026 by czoli1976 Contributor Loading…
1
Feat/gelu f16 lut
#2687 opened Aug 20, 2026 by kali Collaborator Loading…
@kali
1
onnx: accept a MatMulNBits weight that is a constant expression
#2656 opened Aug 17, 2026 by czoli1976 Contributor Loading…
1
5
onnx: import MatMulNBits at bits=2
#2655 opened Aug 17, 2026 by czoli1976 Contributor Loading…
onnx: keep asymmetric MatMulNBits weights block-quantized
#2648 opened Aug 17, 2026 by czoli1976 Contributor Loading…
onnx: import GatherBlockQuantized without widening the table
#2647 opened Aug 17, 2026 by czoli1976 Contributor Loading…
onnx: import GroupQueryAttention decode steps and its internal rotary
#2645 opened Aug 17, 2026 by czoli1976 Contributor Loading…
linalg/mmm: take the chunking slack only where the cache absorbs it
#2570 opened Aug 3, 2026 by czoli1976 Contributor • Draft
1
metal: mlx's preferred implicit-GEMM conv kernel, plus grouped convolutions (1.2-75x)
#2551 opened Aug 1, 2026 by czoli1976 Contributor Loading…
1
metal: depthwise convolution via a ported MLX kernel (2-14x)
#2550 opened Aug 1, 2026 by czoli1976 Contributor Loading…
metal: implicit-GEMM convolution via a ported MLX kernel (9-66x)
#2549 opened Aug 1, 2026 by czoli1976 Contributor Loading…
7
metal: drop the MFA triangular-constant probe test- fails on M1 Pro (macOS 26.5.2) and an M4 (macOS 26.6).
#2546 opened Aug 1, 2026 by czoli1976 Contributor Loading…
nnef: lazy weight loading, so a pruned model never reads what it discards
#2524 opened Jul 26, 2026 by czoli1976 Contributor • Draft
10
Meet Dis-Tract 0.1.0
#2482 opened Jul 16, 2026 by czoli1976 Contributor • Draft
5
bench: add Pocket TTS, DeepFilterNet3 and DTLN to the CI bench suite
#2449 opened Jul 6, 2026 by czoli1976 Contributor • Draft
4
block_quant: role-aware weight quantization policy
#2433 opened Jun 30, 2026 by czoli1976 Contributor • Draft
WIP: W4A8 (Q4_0 int8-dot) path for block_quant — lane-mapped SDOT kernel + wiring
#2432 opened Jun 30, 2026 by czoli1976 Contributor • Draft
1
autobatch: add a cuda-batched runtime that micro-batches concurrent run() …
#2421 opened Jun 29, 2026 by kali Collaborator Loading…
1
RFC: fuse bias/activation epilogue through the einsum unmerge reshape (workload-dependent)
#2415 opened Jun 26, 2026 by czoli1976 Contributor • Draft
ProTip! Type g i on any issue or pull request to go back to the issue listing page.