llm-dequant 0.1.0__tar.gz

llm_dequant-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.

llm_dequant-0.1.0/PKG-INFO

@@ -0,0 +1,184 @@
+Metadata-Version: 2.4
+Name: llm-dequant
+Version: 0.1.0
+Summary: Dequantize compressed-tensors NVFP4 LLM checkpoints to dense safetensors (streaming, constant memory)
+Author: Victor Cruz
+License: Apache-2.0
+Project-URL: Repository, https://github.com/vcruz305/llm-dequant
+Keywords: nvfp4,quantization,dequantization,safetensors,llm,compressed-tensors,gguf
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0
+Requires-Dist: safetensors>=0.4
+Requires-Dist: numpy>=1.24
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Dynamic: license-file
+
+<div align="center">
+
+<img src="llm-dequant.png" alt="llm-dequant — stream NVFP4 compressed-tensors checkpoints back to dense safetensors" width="50%">
+
+**Turn NVFP4-only model releases back into dense safetensors.**
+
+Streaming, constant-memory dequantization of
+[compressed-tensors](https://github.com/neuralmagic/compressed-tensors)
+`nvfp4-pack-quantized` LLM checkpoints — a 300B-parameter MoE converts
+on a few hundred MB of RAM.
+
+[![tests](https://github.com/vcruz305/llm-dequant/actions/workflows/tests.yml/badge.svg)](https://github.com/vcruz305/llm-dequant/actions/workflows/tests.yml)
+[![license](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
+[![python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](pyproject.toml)
+
+</div>
+
+---
+
+## Why this exists
+
+A growing number of community models — abliterations, fine-tunes, supertunes —
+are published **only** in NVFP4 compressed-tensors form. That single release
+format locks out most of the ecosystem:
+
+- `llama.cpp`'s `convert_hf_to_gguf.py` can't read compressed-tensors
+  checkpoints → **no GGUFs**
+- fine-tuning frameworks expect dense weights → **no further training**
+- weight surgery (MTP grafts, merges, pruning) needs real tensors → **no surgery**
+
+The reference decompression path in `compressed-tensors`/`transformers`
+materializes the whole model in memory, which is a non-starter at 300B scale.
+
+`llm-dequant` fixes this with a purpose-built converter:
+
+| | |
+|---|---|
+| 🌊 **Streaming** | module-by-module; peak RSS = one module + one shard buffer |
+| 🎯 **Exact** | output is bit-identical to the reference implementation (CI-checked) |
+| 🧾 **Standard output** | sharded safetensors + index, `quantization_config` stripped, tokenizer files copied — a normal dense HF checkpoint |
+| 🪶 **Dependency-light** | `torch`, `safetensors`, `numpy`. No compressed-tensors, no transformers |
+| 🔍 **Self-verifying** | `verify` proves round-trip byte-equality against *your actual checkpoint* before you commit to a 600GB write |
+| 🛡️ **Defensive** | untrusted `index.json` path names rejected, NaN/Inf scales refuse loudly, unsupported formats never convert silently |
+
+Born from converting a 295B MoE released as NVFP4-only into a full GGUF quant
+sweep ([SuperHY3-abliterated-GGUF](https://huggingface.co/vcruz305/SuperHY3-abliterated-GGUF)).
+
+## Install
+
+```bash
+pip install llm-dequant            # from PyPI (published releases)
+```
+
+or straight from GitHub (works on any commit, no release needed):
+
+```bash
+pip install git+https://github.com/vcruz305/llm-dequant.git
+```
+
+Both pull in `torch`, `safetensors`, and `numpy` automatically. For a
+CPU-only torch (much smaller download):
+
+```bash
+pip install torch --index-url https://download.pytorch.org/whl/cpu
+pip install llm-dequant
+```
+
+## Quickstart
+
+```bash
+# 1. what is this checkpoint?
+llm-dequant inspect /models/SomeModel-NVFP4
+
+# 2. prove the math round-trips on THIS checkpoint (seconds, no writes)
+llm-dequant verify /models/SomeModel-NVFP4 --sample 16
+
+# 3. convert (bf16 default; fp16/fp32 available)
+llm-dequant convert /models/SomeModel-NVFP4 /models/SomeModel-BF16
+```
+
+Then use the output like any dense checkpoint:
+
+```bash
+python llama.cpp/convert_hf_to_gguf.py /models/SomeModel-BF16 \
+    --outfile SomeModel-BF16.gguf --outtype bf16
+```
+
+### Python API
+
+```python
+from llm_dequant.model import convert, verify, inspect_checkpoint
+from llm_dequant.nvfp4 import dequantize_nvfp4, unpack_fp4, pack_fp4
+
+convert("/models/in-nvfp4", "/models/out-bf16", dtype="bf16")
+```
+
+## The NVFP4 format, in one table
+
+`nvfp4-pack-quantized` (emitted by
+[llm-compressor](https://github.com/vllm-project/llm-compressor)) stores, per
+quantized Linear:
+
+| tensor | dtype | shape | meaning |
+|---|---|---|---|
+| `weight_packed` | uint8 | `[m, n/2]` | two FP4-E2M1 codes per byte, low nibble first |
+| `weight_scale` | fp8-e4m3 | `[m, n/16]` | one scale per group of 16 columns |
+| `weight_global_scale` | fp32 | scalar | per-module global scale *(optional)* |
+
+An FP4 code is 1 sign bit + 3 bits indexing the E2M1 magnitude table
+`[0, 0.5, 1, 1.5, 2, 3, 4, 6]`, and
+
+```
+W[i, j] = e2m1(code[i, j]) · scale[i, j//16] / weight_global_scale
+```
+
+**Dequantization is exact.** Every recovered value sits precisely on the
+scaled FP4 lattice (computed in fp32, cast once to the output dtype). Nothing
+the NVFP4 checkpoint encodes is lost. What the original 4-bit quantization
+already destroyed is of course not recoverable — the output is *dense*, not
+*restored*. If you re-quantize the result (e.g. to GGUF), disclose the FP4
+provenance: tiers at or below ~4 bpw lose essentially nothing, higher tiers
+only improve the never-quantized tensors.
+
+## How correctness is established
+
+Two independent layers, both of which you can run yourself:
+
+**1. `llm-dequant verify <src>` — against your checkpoint.**
+Samples random packed modules, dequantizes, renormalizes by the effective
+scale, re-packs with nearest-E2M1 rounding, and requires **byte equality**
+with the original `weight_packed`. Any error in nibble order, scale layout,
+group mapping, or global-scale handling breaks byte equality. (This proves
+self-consistency against the real bytes; spec conformance comes from layer 2.)
+
+**2. The test suite — against the reference implementation.**
+Hand-computed vectors, exhaustive FP4 code tables, property-based round-trips,
+end-to-end synthetic checkpoints (sharded + single-file, with/without global
+scale), corruption and path-traversal rejection, and a bit-exactness test
+against upstream `compressed-tensors` (runs in CI).
+
+```bash
+pip install -e .[dev] && pytest
+```
+
+## Scope
+
+Supported: `format: nvfp4-pack-quantized`, symmetric, `group_size: 16` — the
+only layout llm-compressor emits for NVFP4 today. Fused-MoE expert tensors
+(`[experts, m, n/2]`) work unchanged.
+
+Rejected loudly, never converted silently: other compressed-tensors formats,
+asymmetric quantization (`weight_zero_point`), NaN/Inf scales, shard names
+that escape the checkpoint directory, colliding output tensor names.
+
+Dropped by design: activation-quantization metadata (`input_global_scale`) —
+the output is dense; runtime activation quantization no longer applies.
+
+## License
+
+Apache-2.0. The FP4/E2M1 constant table follows the format specification
+established by the vLLM / compressed-tensors projects (Apache-2.0).

llm_dequant-0.1.0/README.md

@@ -0,0 +1,161 @@
+<div align="center">
+
+<img src="llm-dequant.png" alt="llm-dequant — stream NVFP4 compressed-tensors checkpoints back to dense safetensors" width="50%">
+
+**Turn NVFP4-only model releases back into dense safetensors.**
+
+Streaming, constant-memory dequantization of
+[compressed-tensors](https://github.com/neuralmagic/compressed-tensors)
+`nvfp4-pack-quantized` LLM checkpoints — a 300B-parameter MoE converts
+on a few hundred MB of RAM.
+
+[![tests](https://github.com/vcruz305/llm-dequant/actions/workflows/tests.yml/badge.svg)](https://github.com/vcruz305/llm-dequant/actions/workflows/tests.yml)
+[![license](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
+[![python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](pyproject.toml)
+
+</div>
+
+---
+
+## Why this exists
+
+A growing number of community models — abliterations, fine-tunes, supertunes —
+are published **only** in NVFP4 compressed-tensors form. That single release
+format locks out most of the ecosystem:
+
+- `llama.cpp`'s `convert_hf_to_gguf.py` can't read compressed-tensors
+  checkpoints → **no GGUFs**
+- fine-tuning frameworks expect dense weights → **no further training**
+- weight surgery (MTP grafts, merges, pruning) needs real tensors → **no surgery**
+
+The reference decompression path in `compressed-tensors`/`transformers`
+materializes the whole model in memory, which is a non-starter at 300B scale.
+
+`llm-dequant` fixes this with a purpose-built converter:
+
+| | |
+|---|---|
+| 🌊 **Streaming** | module-by-module; peak RSS = one module + one shard buffer |
+| 🎯 **Exact** | output is bit-identical to the reference implementation (CI-checked) |
+| 🧾 **Standard output** | sharded safetensors + index, `quantization_config` stripped, tokenizer files copied — a normal dense HF checkpoint |
+| 🪶 **Dependency-light** | `torch`, `safetensors`, `numpy`. No compressed-tensors, no transformers |
+| 🔍 **Self-verifying** | `verify` proves round-trip byte-equality against *your actual checkpoint* before you commit to a 600GB write |
+| 🛡️ **Defensive** | untrusted `index.json` path names rejected, NaN/Inf scales refuse loudly, unsupported formats never convert silently |
+
+Born from converting a 295B MoE released as NVFP4-only into a full GGUF quant
+sweep ([SuperHY3-abliterated-GGUF](https://huggingface.co/vcruz305/SuperHY3-abliterated-GGUF)).
+
+## Install
+
+```bash
+pip install llm-dequant            # from PyPI (published releases)
+```
+
+or straight from GitHub (works on any commit, no release needed):
+
+```bash
+pip install git+https://github.com/vcruz305/llm-dequant.git
+```
+
+Both pull in `torch`, `safetensors`, and `numpy` automatically. For a
+CPU-only torch (much smaller download):
+
+```bash
+pip install torch --index-url https://download.pytorch.org/whl/cpu
+pip install llm-dequant
+```
+
+## Quickstart
+
+```bash
+# 1. what is this checkpoint?
+llm-dequant inspect /models/SomeModel-NVFP4
+
+# 2. prove the math round-trips on THIS checkpoint (seconds, no writes)
+llm-dequant verify /models/SomeModel-NVFP4 --sample 16
+
+# 3. convert (bf16 default; fp16/fp32 available)
+llm-dequant convert /models/SomeModel-NVFP4 /models/SomeModel-BF16
+```
+
+Then use the output like any dense checkpoint:
+
+```bash
+python llama.cpp/convert_hf_to_gguf.py /models/SomeModel-BF16 \
+    --outfile SomeModel-BF16.gguf --outtype bf16
+```
+
+### Python API
+
+```python
+from llm_dequant.model import convert, verify, inspect_checkpoint
+from llm_dequant.nvfp4 import dequantize_nvfp4, unpack_fp4, pack_fp4
+
+convert("/models/in-nvfp4", "/models/out-bf16", dtype="bf16")
+```
+
+## The NVFP4 format, in one table
+
+`nvfp4-pack-quantized` (emitted by
+[llm-compressor](https://github.com/vllm-project/llm-compressor)) stores, per
+quantized Linear:
+
+| tensor | dtype | shape | meaning |
+|---|---|---|---|
+| `weight_packed` | uint8 | `[m, n/2]` | two FP4-E2M1 codes per byte, low nibble first |
+| `weight_scale` | fp8-e4m3 | `[m, n/16]` | one scale per group of 16 columns |
+| `weight_global_scale` | fp32 | scalar | per-module global scale *(optional)* |
+
+An FP4 code is 1 sign bit + 3 bits indexing the E2M1 magnitude table
+`[0, 0.5, 1, 1.5, 2, 3, 4, 6]`, and
+
+```
+W[i, j] = e2m1(code[i, j]) · scale[i, j//16] / weight_global_scale
+```
+
+**Dequantization is exact.** Every recovered value sits precisely on the
+scaled FP4 lattice (computed in fp32, cast once to the output dtype). Nothing
+the NVFP4 checkpoint encodes is lost. What the original 4-bit quantization
+already destroyed is of course not recoverable — the output is *dense*, not
+*restored*. If you re-quantize the result (e.g. to GGUF), disclose the FP4
+provenance: tiers at or below ~4 bpw lose essentially nothing, higher tiers
+only improve the never-quantized tensors.
+
+## How correctness is established
+
+Two independent layers, both of which you can run yourself:
+
+**1. `llm-dequant verify <src>` — against your checkpoint.**
+Samples random packed modules, dequantizes, renormalizes by the effective
+scale, re-packs with nearest-E2M1 rounding, and requires **byte equality**
+with the original `weight_packed`. Any error in nibble order, scale layout,
+group mapping, or global-scale handling breaks byte equality. (This proves
+self-consistency against the real bytes; spec conformance comes from layer 2.)
+
+**2. The test suite — against the reference implementation.**
+Hand-computed vectors, exhaustive FP4 code tables, property-based round-trips,
+end-to-end synthetic checkpoints (sharded + single-file, with/without global
+scale), corruption and path-traversal rejection, and a bit-exactness test
+against upstream `compressed-tensors` (runs in CI).
+
+```bash
+pip install -e .[dev] && pytest
+```
+
+## Scope
+
+Supported: `format: nvfp4-pack-quantized`, symmetric, `group_size: 16` — the
+only layout llm-compressor emits for NVFP4 today. Fused-MoE expert tensors
+(`[experts, m, n/2]`) work unchanged.
+
+Rejected loudly, never converted silently: other compressed-tensors formats,
+asymmetric quantization (`weight_zero_point`), NaN/Inf scales, shard names
+that escape the checkpoint directory, colliding output tensor names.
+
+Dropped by design: activation-quantization metadata (`input_global_scale`) —
+the output is dense; runtime activation quantization no longer applies.
+
+## License
+
+Apache-2.0. The FP4/E2M1 constant table follows the format specification
+established by the vLLM / compressed-tensors projects (Apache-2.0).

llm_dequant-0.1.0/pyproject.toml

@@ -0,0 +1,40 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llm-dequant"
+version = "0.1.0"
+description = "Dequantize compressed-tensors NVFP4 LLM checkpoints to dense safetensors (streaming, constant memory)"
+readme = "README.md"
+license = { text = "Apache-2.0" }
+requires-python = ">=3.10"
+authors = [{ name = "Victor Cruz" }]
+keywords = ["nvfp4", "quantization", "dequantization", "safetensors", "llm", "compressed-tensors", "gguf"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "torch>=2.0",
+    "safetensors>=0.4",
+    "numpy>=1.24",  # required by safetensors' save path
+]
+
+[project.scripts]
+llm-dequant = "llm_dequant.cli:main"
+
+[project.urls]
+Repository = "https://github.com/vcruz305/llm-dequant"
+
+[project.optional-dependencies]
+dev = ["pytest>=7"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

llm_dequant-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

llm_dequant-0.1.0/src/llm_dequant/__init__.py

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: Apache-2.0
+"""llm-dequant: dequantize compressed-tensors LLM checkpoints to full-precision safetensors."""
+
+__version__ = "0.1.0"

llm_dequant-0.1.0/src/llm_dequant/cli.py

@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: Apache-2.0
+"""Command-line interface for llm-dequant."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+from . import __version__
+from .model import DEFAULT_SHARD_BYTES, DTYPES, convert, inspect_checkpoint, verify
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(
+        prog="llm-dequant",
+        description=(
+            "Dequantize compressed-tensors NVFP4 checkpoints to dense "
+            "safetensors (streaming, constant memory)."
+        ),
+    )
+    parser.add_argument("--version", action="version", version=__version__)
+    sub = parser.add_subparsers(dest="command", required=True)
+
+    p_convert = sub.add_parser("convert", help="dequantize a checkpoint")
+    p_convert.add_argument("src", type=Path, help="compressed checkpoint directory")
+    p_convert.add_argument("dst", type=Path, help="output directory")
+    p_convert.add_argument(
+        "--dtype", choices=sorted(DTYPES), default="bf16",
+        help="output dtype (default: bf16)",
+    )
+    p_convert.add_argument(
+        "--shard-gb", type=float, default=DEFAULT_SHARD_BYTES / 1024**3,
+        help="target output shard size in GiB (default: 8)",
+    )
+
+    p_verify = sub.add_parser(
+        "verify",
+        help="round-trip check: dequantize + repack sampled modules, compare bytes",
+    )
+    p_verify.add_argument("src", type=Path, help="compressed checkpoint directory")
+    p_verify.add_argument("--sample", type=int, default=8,
+                          help="number of random packed modules to check (default: 8)")
+    p_verify.add_argument("--seed", type=int, default=0, help="sampling seed")
+
+    p_inspect = sub.add_parser("inspect", help="show checkpoint quantization summary")
+    p_inspect.add_argument("src", type=Path, help="checkpoint directory")
+
+    args = parser.parse_args(argv)
+
+    try:
+        if args.command == "convert":
+            if args.shard_gb <= 0:
+                parser.error("--shard-gb must be positive")
+            convert(args.src, args.dst, dtype=args.dtype,
+                    shard_bytes=int(args.shard_gb * 1024**3))
+        elif args.command == "verify":
+            result = verify(args.src, sample=args.sample, seed=args.seed)
+            return 0 if not result["failures"] else 1
+        elif args.command == "inspect":
+            inspect_checkpoint(args.src)
+    except (FileNotFoundError, ValueError) as exc:
+        print(f"error: {exc}", file=sys.stderr)
+        return 2
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())