vh
069725c4b3
services/semif-serve is a FastAPI wrapper around SemIf's direct and shared torch scorers (SemIf-OpenJev @ 23cf1f39, MIT). Upstream ships only a batch CLI. The wrapper loads the pinned Qwen3.5-4B (851bf6e8, BF16) once from the offline HF cache and returns SemIf's result dicts unchanged, with an optional per-workload temperature-calibrated view. Contract: semif-serve.contract.md. Built with a short contract, TDD (39 tests, fake engine and fake torch, no GPU) and a heid bug-hunt panel (pending). On the card: - torch 2.10.0+cu128 with sm_120 kernels, which is SemIf's own stack; - a hard 12 GiB VRAM cap. Two defects surfaced only on the card, and each fix is covered by a test: - 0.1.1: an OOM raised as a chained exception kept the failed request's tensors alive (11.9 GiB after the 503). It is now raised unchained, after gc. - 0.1.2: a large request left 12.6 GB reserved on the shared card. After each call, reserved memory over the baseline + 512 MiB is now released. Acceptance against SemIf's committed torch predictions (authored144): - 142/144 same top choice; both misses are exact bf16 ties; - 144/144 identical prompt hashes; - deterministic A-vs-A; - negative control 14/144; - shared vs direct 72/72. 21 binary criteria over one state take 159 ms. The shared-mode capacity table under the cap is in stacks/semif/README.md. The Dockerfile installs dependencies from a manifest with the project version blanked, so a version bump reuses the ~4 GB torch layer. Verified: 41 s rebuild, dependency layer CACHED. DNS: semif.fv.internal. Token: vault semif/api-token.
40 lines
1.0 KiB
TOML
40 lines
1.0 KiB
TOML
[project]
|
|
name = "semif-serve"
|
|
version = "0.1.2"
|
|
description = "HTTP wrapper around SemIf's direct and shared option-logit scorers"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"fastapi==0.118.0",
|
|
"uvicorn==0.37.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
# The real engine. Pulls torch 2.10.0 (cu128) and transformers 5.17.0 through SemIf's exact pins.
|
|
model = [
|
|
"semif-phase1 @ git+https://github.com/TheoLeeCJ/SemIf-OpenJev@23cf1f39fc9534fe81437200959b6dfc7106e45a",
|
|
# Same pin SemIf declares, taken from the cu128 index: SemIf's committed predictions report
|
|
# torch 2.10.0+cu128, and cu128 carries sm_120 kernels for the Blackwell cards.
|
|
"torch==2.10.0",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = ["pytest==8.4.2", "httpx==0.28.1"]
|
|
|
|
[build-system]
|
|
requires = ["setuptools>=68"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cu128"
|
|
url = "https://download.pytorch.org/whl/cu128"
|
|
explicit = true
|
|
|
|
[tool.uv.sources]
|
|
torch = { index = "pytorch-cu128" }
|