infersize 0.2.0__tar.gz

infersize-0.2.0/.github/workflows/ci.yml

@@ -0,0 +1,41 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    name: Test (${{ matrix.os }}, Py${{ matrix.python-version }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.11", "3.12"]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Lint checks (Ruff)
+        run: uv run ruff check src tests
+
+      - name: Formatting check (Ruff)
+        run: uv run ruff format --check src tests
+
+      - name: Run test suite
+        run: uv run pytest -v

infersize-0.2.0/.github/workflows/release.yml

@@ -0,0 +1,43 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  build:
+    name: Build package
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+      - name: Build sdist and wheel
+        run: uv build
+      - name: Store distributions
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-pypi:
+    name: Publish to PyPI
+    needs: [build]
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/infersize
+    permissions:
+      id-token: write
+    steps:
+      - name: Download distributions
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true

infersize-0.2.0/.gitignore

@@ -0,0 +1,39 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+dist/
+site/
+.ruff_cache/
+

infersize-0.2.0/DEVLOG.md

@@ -0,0 +1,91 @@
+# DEVLOG: infersize
+
+## 2026-10-29: Project Inception & Phase 1 VRAM Capacity Modeling
+
+- Initialized Project #5 `infersize` (Analytical Performance Modeling & VRAM Capacity Planner for LLM Serving).
+- Strategic positioning: Pure-Python, zero-dependency analytical performance modeling tool predicting VRAM limits, KV-cache footprints, and hardware roofline saturation before spending money on cloud GPU compute.
+- Initialized Apache 2.0 license, `.gitignore`, and `pyproject.toml` with `hatchling` build backend and `uv` package manager.
+- Implemented Phase 1 Analytical VRAM Engine:
+  - Exact transformer parameter accounting from model configuration (Embeddings, Q/K/V/O projections, SwiGLU dense/MoE FFNs, RMSNorms).
+  - Open-weights model presets: Qwen 2.5 (0.5B, 1.5B, 7B, 14B, 32B, 72B), Llama 3 (8B, 70B), Mistral 7B, Phi-3 Mini, GPT-2.
+  - Hardware profiles: NVIDIA RTX 3050, RTX 4060, RTX 4090, Tesla T4, L4, A100 (40GB/80GB), H100 (80GB), H200 (141GB), Apple M3 Max (36GB/128GB).
+  - Multi-precision weight footprint calculation (FP32, FP16/BF16, INT8/FP8, INT4/FP4, BitNet 1.58b).
+  - Exact KV-cache memory equation: $2 \times L \times H_{\text{kv}} \times D \times B$.
+  - Maximum context window solver (`find_max_context_length`) and concurrent stream solver (`find_max_concurrent_batch_size`).
+- Implemented rich Typer CLI (`infersize`):
+  - `vram`: Detailed component memory breakdown (weights, KV, activations, driver) with visual ASCII allocation bar.
+  - `max-batch`: Safe concurrent serving stream sizing.
+  - `max-context`: Context window capacity before OOM.
+  - `models` & `gpus`: Catalog tables with architecture stats and Silicon ridge points.
+- 6/6 unit test suites passing with 100% assertions verified. All Ruff checks passing.
+
+---
+
+## 2026-10-30: PR #1 - Multi-GPU Hardware Comparison Matrix Engine
+
+- **Branch**: `feat/gpu-comparison-matrix` -> **Merged via PR #1**.
+- Implemented `infersize.analytics.comparison.compare_gpus_for_workload`:
+  - Evaluates target serving workloads (model, quant, KV dtype, batch size, context length, TP) across all candidate accelerators in parallel.
+  - Computes exact memory required, headroom deficit, utilization percentage, max concurrent batch size, and memory bandwidth for each GPU.
+  - Automated procurement sizing heuristics:
+    - **Right-Sized / Cost-Effective GPU**: Minimal idle VRAM waste, lowest hardware tier fitting the workload safely.
+    - **Peak Throughput GPU**: Highest memory bandwidth among fitting GPUs.
+- Implemented CLI command `infersize compare`:
+  - Rich-formatted side-by-side terminal comparison table with status indicators (`⭐ OPTIMAL`, `✔ FITS`, `ℹ OVERKILL`, `✘ OOM`).
+  - `--gpus` filtering (e.g. `--gpus rtx4090,a100-80gb,l4`).
+  - `--json` machine-readable output format for infrastructure CI gates.
+  - `to_markdown()` Markdown table generator for documentation export.
+- Added 7 comprehensive unit tests in `tests/test_comparison.py`.
+
+---
+
+## 2026-10-30: PR #2 - Cloud Cost & Memory-Bandwidth Decode Roofline Engine
+
+- **Branch**: `feat/cloud-cost-calculator` -> **Merged via PR #2**.
+- Implemented `infersize.analytics.cost`:
+  - Memory-bandwidth bound autoregressive decode throughput roofline modeling:
+    $$\text{Decode Throughput (tok/s)} = \frac{B \cdot \text{BW} \cdot \eta}{W_{\text{bytes}} + \text{KV}_{\text{bytes}}}$$
+  - Computes Time Per Output Token (TPOT latency per user stream in ms).
+  - Computes exact unit operational economics: **\$ / 1 Million Tokens** and monthly 24/7 dedicated hosting cost (730 continuous hours).
+  - Built-in cloud GPU pricing registry (`infersize.hardware.pricing`) for **RunPod**, **Lambda Labs**, **AWS EC2**, and **Google Cloud (GCP)**.
+- Implemented CLI command `infersize cost`:
+  - Panel header with workload summary, cluster cost, and fitting status.
+  - Full metrics breakdown table with physical and financial engineering insights.
+  - `--compare-clouds`: Side-by-side price comparison across all supported cloud providers for a single GPU.
+  - `--compare-all`: Multi-accelerator cost, throughput, and $/1M tokens comparison matrix.
+  - `--rate`: Custom hourly rental rate override per GPU.
+- Added 9 unit tests in `tests/test_cost.py` verifying throughput, TP cluster cost, and cloud price lookups.
+
+---
+
+## 2026-10-30: PR #3 - Architecture RFC Report Generator & v0.2.0 Bump
+
+- **Branch**: `feat/report-export` -> **Merged via PR #3**.
+- Implemented `infersize.analytics.report.generate_architecture_report`:
+  - Synthesizes workload configuration, physical memory breakdowns, multi-GPU comparison matrix, and cloud TCO economics into an engineering specification.
+  - Exports publication-ready Markdown RFC specifications (`to_markdown()`) ready to drop into GitHub PRs, Engineering RFCs, or infrastructure tickets.
+  - Formulates LaTeX equations for KV-cache, decode roofline throughput, and unit economics.
+- Implemented CLI command `infersize report`:
+  - Renders syntax-highlighted Markdown directly to terminal console or writes directly to file via `--output <path.md>`.
+  - Machine-readable `--json` schema output for automated DevOps pipelines.
+- Bumped package version to `v0.2.0` in `pyproject.toml` and `src/infersize/__init__.py`.
+- Added 6 unit tests in `tests/test_report.py`.
+
+---
+
+## 2026-10-31: PR #4 - Dynamic Hugging Face Hub Auto-Ingestion, MoE Active Parameter Sizing & PyPI Release CI
+
+- **Branch**: `feat/hf-auto-spec` -> **Merged via PR #4**.
+- Implemented `src/infersize/models/loader.py`:
+  - Dynamic Hugging Face Hub `config.json` ingestion using Python standard library `urllib.request`. Zero external heavy dependencies (no PyTorch, Transformers, or Hugging Face Hub SDK required).
+  - Fetches and parses any open-weights architecture in <300ms from `https://huggingface.co/<org>/<repo>/raw/main/config.json`.
+  - Local custom file support via `load_model_arch_from_config(path)`.
+  - Automatic repo name detection: string containing `/` (e.g. `meta-llama/Llama-3.1-8B-Instruct`, `Qwen/Qwen2.5-7B`) triggers automatic Hub resolution.
+  - Gated model authorization via `--hf-token` or `HF_TOKEN` environment variable.
+- Mixture-of-Experts (MoE) Physical Sizing:
+  - Differentiated **Total Parameters** ($E$ experts held in static VRAM) from **Active Parameters** (top-$K$ routed experts streaming per token step).
+  - Added `ModelArch.calculate_active_parameters()` in `specs.py`.
+  - Updated decode memory traffic in `cost.py` to stream active parameters across the memory bus, matching true vLLM/SGLang/TensorRT-LLM decode physics.
+- Wired `--hf`, `--config`, and `--hf-token` across all CLI commands (`vram`, `compare`, `cost`, `report`, `max-batch`, `max-context`).
+- Added PyPI Trusted Publisher automated workflow in `.github/workflows/release.yml`.
+- Added 8 unit tests in `tests/test_hf_loader.py`. Test suite expanded to 36 tests with 95% code coverage and zero Ruff warnings.

infersize-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Prajwal Pujari
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.