Skip to content

Pull requests: sonos/tract

New pull request New
32 Open 2,073 Closed
32 Open 2,073 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

metal: accumulate the matmul test reference in f32 to match the kernels
#2463 opened Jul 10, 2026 by kali Collaborator Loading…
1
bench: let append-dinghy run per-leg so one stuck board doesn't drop …
#2462 opened Jul 10, 2026 by kali Collaborator Loading…
1
transformers: quantized KV-cache storage op (int8/int4)
#2458 opened Jul 8, 2026 by czoli1976 Contributor Loading…
cpu decode: route f16 SDPA through FlashSdpa, fuse GQA broadcast through cache-read cast/rope
#2453 opened Jul 6, 2026 by czoli1976 Contributor Loading…
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
linalg/block_quant: W4A8 GEMM for Q4_0 (int8-dot decode path)
#2431 opened Jun 30, 2026 by czoli1976 Contributor Loading…
block_quant: quantize einsum weights at either input slot
#2428 opened Jun 30, 2026 by czoli1976 Contributor Loading…
cuda: add a cuda-batched runtime that micro-batches concurrent run() …
#2421 opened Jun 29, 2026 by kali Collaborator Loading…
1
Quality: u32 overflow in CUDA grid dimension calculation silently truncates large tensor indices
#2417 opened Jun 27, 2026 by kumburovicbranko682-boop Loading…
3 tasks
4
RFC: fuse bias/activation epilogue through the einsum unmerge reshape (workload-dependent)
#2415 opened Jun 26, 2026 by czoli1976 Contributor • Draft
fix(data): reject raw tensor whose data length != declared shape (#2390)
#2413 opened Jun 25, 2026 by czoli1976 Contributor Loading…
1
1
onnx: don't panic on absent TensorProto/GraphProto attribute field (#2372)
#2412 opened Jun 25, 2026 by czoli1976 Contributor Loading…
1
2
fix: prevent panics in shape inference when operands missing
#2411 opened Jun 25, 2026 by jaweed3 Contributor Loading…
1
1
RFC: future-looking emulated ACE (AI Compute Extensions) matrix backend
#2397 opened Jun 21, 2026 by czoli1976 Contributor • Draft
linalg/x86_64: optimize softmax instruction scheduling with interleaved fmadd/vmaxps
#2396 opened Jun 20, 2026 by czoli1976 Contributor Loading…
1
metal/ggml: keep q4_0 decode on the mat-vec kernel up to 8 rows
#2369 opened Jun 14, 2026 by czoli1976 Contributor Loading…
metal: pack element-wise kernels into full-width threadgroups
#2365 opened Jun 13, 2026 by czoli1976 Contributor • Draft
5
linalg/arm64/sme: experimental f16 SME kernels for Apple M5/A19 Need tester with hardware
#2273 opened May 22, 2026 by czoli1976 Contributor • Draft
feat: add tract_moe_ffn operator for Mixture-of-Experts FFN
#2084 opened Mar 30, 2026 by JulienBalianSonos Collaborator Loading…
1
Flux schnell
#2082 opened Mar 30, 2026 by kali Collaborator Loading…
Refactor nemo examples
#2006 opened Mar 5, 2026 by kali Collaborator • Draft
tolerate / in id names
#1885 opened Oct 16, 2025 by kali Collaborator • Draft
[DRAFT] Feat/vptq proto
#1627 opened Jan 29, 2025 by JulienBalianSonos Collaborator • Draft
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.