Breadway/breadsearch
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Migrate embedding pipeline, EP session building, and model download to bread-onnx

Browse source 
embed.rs's OrtEmbedder now delegates its tokenize -> tensor build ->
mean-pool -> L2-normalize pipeline to bread_onnx::embedding::EmbeddingSession
(near-byte-identical to breadarrd's own OrtEmbedder — same duplication, now
shared, path dependency for now, see the TODO in breadmill/Cargo.toml), and
its per-EP session builders (npu_session/rocm_session/cuda_session/
openvino_session) collapse into a single to_provider() mapping onto
bread_onnx::Provider, which this crate's own breadmill/src/session.rs
counterpart now handles generically. This crate's Backend enum, cargo
feature gates (npu/rocm/cuda/openvino/full - unchanged, still control which
onnxruntime EPs actually link/load), and NPU vaip_config.json discovery all
stay local since they're genuinely breadsearch-specific. main.rs's Backend
construction and CLI flag handling are untouched.

This is also the reference implementation the MIGraphX-not-ROCm default in
bread-onnx's provider module was promoted from (see this machine's own
breadsearch-gpu-backends operator notes) — breadpad's ONNX migration, which
had the actual silent-fallback bug, follows in a later commit.

download_if_missing is replaced with bread_onnx::download::ensure_file
(same sync/ureq approach, now shared with breadarrd's downloader).

Builds clean with default features AND --features full (npu+rocm+cuda+
openvino all compiling together, matching how this crate already combined
them). All existing tests pass across the whole workspace.
This commit is contained in:
Breadway 2026-07-17 09:41:58 +08:00
parent d01a3841d9
commit 0990969722
4 changed files with 88 additions and 231 deletions
Download patch file Download diff file Expand all files Collapse all files

2
breadmill/Cargo.toml
View file

@ -42,6 +42,8 @@ breadsearch-shared = { path = "../breadsearch-shared" }
# needed for the plain CPU path even in the npu build.
ort = { version = "2.0.0-rc.12", default-features = false, features = ["std", "tracing", "download-binaries", "tls-native", "copy-dylibs", "api-23"] }
tokenizers = "0"
# TODO(owner): switch to tag-pinned git dependency once bread-onnx is merged and tagged, matching the bread-theme pattern
bread-onnx = { path = "../../bread-ecosystem-fix-worktree/bread-onnx" }
# Surfaces ort's own EP-registration tracing (e.g. a GPU EP silently failing to
# register and falling back to CPU) as visible log output instead of nowhere.