unalloc 0.2.0__tar.gz → 0.2.1__tar.gz

{unalloc-0.2.0 → unalloc-0.2.1}/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.2.1 — 2026-09-14
+
+### Changed
+- Paper prepared for arXiv: abstract leads with the attribution failures at the seams between ledgers and the H100 result; metering results are framed as disagreement between rules rather than over-charging, since none is a ground truth; new Related Work section (JouleShare, LLMVisor, PrefixShield, Cost-Governed RAG and others); defect catalogue moved to Appendix A; use of AI tools disclosed.
+- `paper/build.py` fails on Typst that compiles but renders wrong (`~`, `;` after a citation, unescaped dollar amounts).
+
+### Added
+- `case_studies/gpu_validation`: benchmark client, fake server, remote setup script, analysis and evidence renderer for validating the metering results with real vLLM on a GPU, plus a DigitalOcean runbook. First run: H100, vLLM 0.29.0, Qwen2.5-7B-Instruct, 6,241 requests, 0 errors.
+- Blog addendum with the verified GPU specs, results and bring-up/teardown evidence.
+- Paper §9, "Validation on a datacenter GPU", with the H100 results table and figure; abstract, methodology table and limitations updated to match.
+
 ## 0.2.0 — 2026-09-13
 
 Validated against five inference case studies; see `paper/unalloc-case-studies.pdf`.

{unalloc-0.2.0 → unalloc-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: unalloc
-Version: 0.2.0
+Version: 0.2.1
 Summary: Find the AI spend nobody owns. Joins OpenCost allocation data with LLM provider bills and reports what's unattributed.
 Project-URL: Homepage, https://github.com/timurista/unalloc
 Project-URL: Issues, https://github.com/timurista/unalloc/issues
@@ -198,6 +198,7 @@ Five studies push real (or realistically simulated) inference workloads through
 | [`distributed`](https://github.com/timurista/unalloc/blob/main/case_studies/distributed) | Tensor and pipeline parallel on `torch.distributed` (gloo), verified against a single-process reference | Owner label on LeaderWorkerSet leaders only: 66% unallocated; falling back to `name` "fixes" it by sending 61% to a Helm chart name |
 | [`hybrid_e2e`](https://github.com/timurista/unalloc/blob/main/case_studies/hybrid_e2e) | The real CLI as a subprocess against live mock OpenCost / LiteLLM / OpenAI / Anthropic APIs (Postgres-backed LiteLLM in the dev container) | Enabling every source double counts $11.8K; reading only page one of the billing APIs reports 25% of spend |
 | [`use_cases`](https://github.com/timurista/unalloc/blob/main/case_studies/use_cases) | Labeling Pareto, per-feature unit economics, self-host break-even, CI budget gate | Three label fixes take a 67%-unallocated org under 10% |
+| [`gpu_validation`](https://github.com/timurista/unalloc/blob/main/case_studies/gpu_validation) | Real vLLM 0.29 serving Qwen2.5-7B on a DigitalOcean H100, driven with the simulator's tenants ([runbook](https://github.com/timurista/unalloc/blob/main/case_studies/gpu_validation/RUNBOOK.md), [evidence](https://github.com/timurista/unalloc/tree/main/case_studies/results/gpu_validation/evidence)) | Token metering over-charges search by 12–14 points vs time share; GPU "utilization" reads 97% at 2 req/s and 99% at 16 req/s |
 
 ```bash
 make research            # CPU torch, notebook tooling, typst

{unalloc-0.2.0 → unalloc-0.2.1}/README.md

@@ -157,6 +157,7 @@ Five studies push real (or realistically simulated) inference workloads through
 | [`distributed`](https://github.com/timurista/unalloc/blob/main/case_studies/distributed) | Tensor and pipeline parallel on `torch.distributed` (gloo), verified against a single-process reference | Owner label on LeaderWorkerSet leaders only: 66% unallocated; falling back to `name` "fixes" it by sending 61% to a Helm chart name |
 | [`hybrid_e2e`](https://github.com/timurista/unalloc/blob/main/case_studies/hybrid_e2e) | The real CLI as a subprocess against live mock OpenCost / LiteLLM / OpenAI / Anthropic APIs (Postgres-backed LiteLLM in the dev container) | Enabling every source double counts $11.8K; reading only page one of the billing APIs reports 25% of spend |
 | [`use_cases`](https://github.com/timurista/unalloc/blob/main/case_studies/use_cases) | Labeling Pareto, per-feature unit economics, self-host break-even, CI budget gate | Three label fixes take a 67%-unallocated org under 10% |
+| [`gpu_validation`](https://github.com/timurista/unalloc/blob/main/case_studies/gpu_validation) | Real vLLM 0.29 serving Qwen2.5-7B on a DigitalOcean H100, driven with the simulator's tenants ([runbook](https://github.com/timurista/unalloc/blob/main/case_studies/gpu_validation/RUNBOOK.md), [evidence](https://github.com/timurista/unalloc/tree/main/case_studies/results/gpu_validation/evidence)) | Token metering over-charges search by 12–14 points vs time share; GPU "utilization" reads 97% at 2 req/s and 99% at 16 req/s |
 
 ```bash
 make research            # CPU torch, notebook tooling, typst

{unalloc-0.2.0 → unalloc-0.2.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "unalloc"
-version = "0.2.0"
+version = "0.2.1"
 description = "Find the AI spend nobody owns. Joins OpenCost allocation data with LLM provider bills and reports what's unattributed."
 readme = "README.md"
 requires-python = ">=3.11"

{unalloc-0.2.0 → unalloc-0.2.1}/src/unalloc/__init__.py

@@ -2,5 +2,5 @@
 
 from __future__ import annotations
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __all__ = ["__version__"]

unalloc-0.2.1/tests/test_paper_lint.py

@@ -0,0 +1,30 @@
+"""The paper build refuses Typst that compiles but renders wrong."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT))
+
+from paper.build import SOURCE, lint_source  # noqa: E402
+
+
+def test_published_paper_source_is_clean():
+    assert lint_source(SOURCE.read_text()) == []
+
+
+def test_tilde_is_flagged_in_prose_but_not_in_code():
+    assert lint_source("reads only ~25% of spend") == [
+        "line 1: `~` renders as a non-breaking space; write ≈ or 'about'"
+    ]
+    assert lint_source("run `ls ~/.ssh` first") == []
+    assert lint_source("```\ncd ~/unalloc\n```") == []
+
+
+def test_semicolon_after_citation_and_bare_dollar_are_flagged():
+    assert lint_source('prefills #c("sarathi"); step latency')
+    assert lint_source("costs $5,703 per month")
+    assert lint_source("costs \\$5,703 per month") == []
+    assert lint_source("where $U > P$ holds") == []