Commit graph

7 commits

Author SHA1 Message Date
Breadway
993dc4a525 Fix cargo clippy warnings across the workspace
All checks were successful
dev release / build (push) Successful in 4m4s
- Derive Default for Config instead of manually mirroring each
  sub-config's Default impl
- Use std::io::Error::other instead of Error::new(ErrorKind::Other, ..)
- Drop the unused mut on the store lock in full_reindex
- Remove Store::dim, a field that was set once and never read
- Use char_indices().enumerate() instead of a hand-rolled loop counter
  in split_by_chars, and is_multiple_of() for the chunk boundary check
- Use strip_prefix instead of manual slicing in expand_home

(cherry picked from commit b740af38e17d04bd83db93bbb0585ed5744a436e)
2026-08-23 14:57:59 +08:00
Breadway
1ce5f72819 Bump version to v0.3.3
All checks were successful
beta (rc) release / build (push) Has been skipped
dev release / build (push) Successful in 6m7s
release / build (push) Successful in 5m34s
2026-08-16 14:09:28 +08:00
Breadway
e20c64fa1a Bump version to v0.3.1
All checks were successful
beta (rc) release / build (push) Has been skipped
dev release / build (push) Successful in 2m29s
release / build (push) Successful in 2m29s
2026-08-15 23:05:47 +08:00
Breadway
99724853a0 Switch to tag-pinned bread-ecosystem deps; bump version to v0.3.0
All checks were successful
Mirror to GitHub / mirror (push) Successful in 2s
release / build (push) Successful in 2m11s
2026-07-19 03:53:04 +08:00
Breadway
c6ed6a41d8 Add OpenVINO backend for Intel iGPU/dGPU (Arc)
All checks were successful
Mirror to GitHub / mirror (push) Successful in 1s
release / build (push) Successful in 2m12s
Mirrors the rocm/cuda pattern: ort::ep::OpenVINO with device_type "GPU"
(covers both Intel integrated graphics and Arc discrete GPUs through the
same EP), load-dynamic/dlopen so no OpenVINO toolkit is needed at build
time, and its own --openvino flag / backend = "openvino" config value.
Folded into the `full` feature alongside npu/rocm/cuda.

OpenVINO's provider options go through a generic key/value FFI interface
rather than a fixed C struct (unlike MIGraphX's OrtMIGraphXProviderOptions),
so it should be less exposed to the ABI-version-skew crash MIGraphX hit --
but that's inference from the EP's design, not verified against real
hardware. Like CUDA, this is compile-checked only: no Intel GPU in this
dev environment to runtime-verify against.

Version bump: breadmill 0.2.2 -> 0.2.3.
2026-07-03 22:58:27 +08:00
Breadway
2618a33fd5 Fix ROCm backend (target MIGraphX EP) and add CUDA support
All checks were successful
Mirror to GitHub / mirror (push) Successful in 1s
release / build (push) Successful in 1m50s
ROCm silently fell back to CPU: the code targeted ONNX Runtime's classic
ROCMExecutionProvider, but distro ROCm-enabled ONNX Runtime builds (e.g.
Arch's onnxruntime-rocm) are commonly compiled with --use_migraphx instead,
and registration failures were invisible since breadmill never installed a
tracing subscriber. Switches the rocm feature to target MIGraphX, adds a
default tracing subscriber so EP registration success/failure is always
visible, and fixes a real crash where MIGraphX's output sequence padding
could index the attention mask out of bounds during mean-pooling.

Also adds a CUDA backend (--cuda / backend = "cuda") mirroring the same
ort execution-provider pattern, for NVIDIA hardware.

Version bump: 0.1.0 -> 0.2.0.
2026-07-03 21:58:39 +08:00
Breadway
2778f14574 Initial commit 2026-07-02 20:59:18 +08:00