-
Notifications
You must be signed in to change notification settings - Fork 268
Pull requests: sonos/tract
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
cpu decode: route f16 SDPA through FlashSdpa, fuse GQA broadcast through cache-read cast/rope
#2453
opened Jul 6, 2026 by
czoli1976
Contributor
Loading…
build(deps): bump the rust-dependencies group across 1 directory with 2 updates
dependencies
Pull requests that update a dependency file
rust
Pull requests that update rust code
#2452
opened Jul 6, 2026 by
dependabot
Bot
Loading…
build(deps): bump the actions group with 3 updates
dependencies
Pull requests that update a dependency file
github_actions
Pull requests that update GitHub Actions code
#2451
opened Jul 6, 2026 by
dependabot
Bot
Loading…
build(deps): bump setuptools-rust from 1.12.1 to 1.13.0 in /api/py
dependencies
Pull requests that update a dependency file
python
Pull requests that update python code
#2450
opened Jul 6, 2026 by
dependabot
Bot
Loading…
MatMulNBits: report not stateless to skip eager const-eval
#2445
opened Jul 6, 2026 by
Reza2kn
Contributor
Loading…
onnx: fix onesided DFT shape inference and slice axis
#2444
opened Jul 4, 2026 by
Adel-Ayoub
Loading…
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…
Quality: u32 overflow in CUDA grid dimension calculation silently truncates large tensor indices
#2417
opened Jun 27, 2026 by
kumburovicbranko682-boop
Loading…
3 tasks
fix(data): reject raw tensor whose data length != declared shape (#2390)
#2413
opened Jun 25, 2026 by
czoli1976
Contributor
Loading…
onnx: don't panic on absent TensorProto/GraphProto attribute field (#2372)
#2412
opened Jun 25, 2026 by
czoli1976
Contributor
Loading…
fix: prevent panics in shape inference when operands missing
#2411
opened Jun 25, 2026 by
jaweed3
Contributor
Loading…
linalg/x86_64: optimize softmax instruction scheduling with interleaved fmadd/vmaxps
#2396
opened Jun 20, 2026 by
czoli1976
Contributor
Loading…
metal/ggml: keep q4_0 decode on the mat-vec kernel up to 8 rows
#2369
opened Jun 14, 2026 by
czoli1976
Contributor
Loading…
feat: add tract_moe_ffn operator for Mixture-of-Experts FFN
#2084
opened Mar 30, 2026 by
JulienBalianSonos
Collaborator
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-07-04.