Interpret and manipulate the internals of deep learning models
Documentation | GitHub | Discord | Forum | Twitter | Paper
About
nnsight lets you get inside a model's forward pass. Open a with model.trace(...)
block and write ordinary Python against any internal value — a layer's output, an
attention pattern, a gradient — as if you already had it: read it, edit it, save it.
You don't register hooks or refactor the model; you write the intervention in the
order it happens, and nnsight runs it interleaved with the real forward pass.
The same trace runs on a model on your laptop or, with remote=True, on a model far
too large for it via the NDIF infrastructure. nnsight works with
any PyTorch model and ships wrappers for HuggingFace, diffusers, and vLLM.
📖 For how it works under the hood — tracing, interleaving, the envoy tree — read NNsight.md. Task recipes live under
docs/.
Installation
pip install nnsight
Quick start
from nnsight import TransformersModel
model = TransformersModel("openai-community/gpt2", dispatch=True)
with model.trace("The Eiffel Tower is in the city of"):
# edit a layer's output in place — the model computes on the edited value
model.transformer.h[0].output[:] = 0
# read a hidden state further down (a [batch, seq, hidden] tensor)
hidden = model.transformer.h[6].output.save()
# keep the final logits
logits = model.output.logits.save()
print(hidden.shape) # torch.Size([1, 10, 768])
print(logits.argmax(-1)) # next-token predictions
Inside the block you're not running the model — you're describing what to do when it
runs. Reading .output gives you the real tensor once the model reaches that module;
assigning to it splices your value in. Mark anything you want after the block with
.save() (or nnsight.save(x)).
A GPT-2 block's
.outputis a plain tensor; some modules (like attention) return a tuple, so you'd index.output[0].print(model)orprint(module.source)shows the shape.
What you can do
Generate — generate returns token ids on tracer.result:
with model.generate("The Eiffel Tower is in", max_new_tokens=3) as tracer:
ids = tracer.result.save()
print(model.tokenizer.decode(ids[0])) # "The Eiffel Tower is in the middle of"
Reach into each generation step — save a container, append raw values (use a bounded range so code after the loop still runs):
import nnsight
with model.generate("Hello", max_new_tokens=5) as tracer:
tokens = nnsight.save([])
for step in tracer.iter[:5]:
tokens.append(model.output.logits[0, -1].argmax(-1))
Batch several prompts in one pass — each invoke block sees only its own rows:
with model.trace() as tracer:
with tracer.invoke("The Eiffel Tower is in"):
eiffel = model.transformer.h[-1].output[:, -1].save()
with tracer.invoke("The Great Wall is in"):
wall = model.transformer.h[-1].output[:, -1].save()
Take gradients with respect to an internal value:
with model.trace("The Eiffel Tower is in the city of"):
hidden = model.transformer.h[-1].output
with model.output.logits.sum().backward():
grad = hidden.grad.save()
Apply modules out of order (a logit lens — decode a middle layer through the head):
with model.trace("The Eiffel Tower is in the city of"):
hidden = model.transformer.h[-1].output
token = model.lm_head(model.transformer.ln_f(hidden))[0, -1].argmax(-1).save()
print(model.tokenizer.decode(token)) # " Paris"
Run it remotely on NDIF — the same trace, on a model you can't host:
from nnsight import CONFIG
CONFIG.set_default_api_key("YOUR_NDIF_KEY")
model = TransformersModel("meta-llama/Llama-3.1-8B")
with model.trace("The Eiffel Tower is in", remote=True):
hidden = model.model.layers[-1].output.save()
There's more — source tracing into a module's forward (.source), persistent
edit(), skip(), scan() for shapes, cache(), session(),
and the vLLM and diffusion runtimes. See docs/ and
NNsight.md.
Your own model
Any torch.nn.Module works — wrap it in NNsight and the whole tree becomes
traceable:
import torch
from nnsight import NNsight
net = torch.nn.Sequential(torch.nn.Linear(5, 10), torch.nn.Linear(10, 2))
model = NNsight(net)
with model.trace(torch.rand(1, 5)):
model[0].output[:] = 0 # zero the first layer's output
out = model.output.save()
print(out) # [1, 2], computed with layer 0 zeroed
Using nnsight from an LLM agent
Give an agent up-to-date nnsight knowledge one of these ways:
- Skills — in Claude Code:
/plugin marketplace add https://github.com/ndif-team/skills.gitthen/plugin install nnsight@skills. In OpenAI Codex:skill-installer install https://github.com/ndif-team/skills.git. - Context7 MCP — add
use context7to prompts, or point your MCP client athttps://mcp.context7.com/mcp(see Context7). - Docs in context — hand the agent CLAUDE.md (routes to the task docs) and NNsight.md (the internals).
Learn more
- nnsight.net — tutorials, guides, API reference
- NNsight.md — the design-and-implementation manual
- docs/index.md (routed for agents by CLAUDE.md) — the task reference
- nnsight.net/status — models available on NDIF
Citation
If you use nnsight in your research, please cite:
@article{fiottokaufman2024nnsightndifdemocratizingaccess,
title={NNsight and NDIF: Democratizing Access to Foundation Model Internals},
author={Jaden Fiotto-Kaufman and Alexander R Loftus and Eric Todd and Jannik Brinkmann and Caden Juang and Koyena Pal and Can Rager and Aaron Mueller and Samuel Marks and Arnab Sen Sharma and Francesca Lucchetti and Michael Ripa and Adam Belfki and Nikhil Prakash and Sumeet Multani and Carla Brodley and Arjun Guha and Jonathan Bell and Byron Wallace and David Bau},
year={2024},
eprint={2407.14561},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2407.14561},
}
1 maintainer
Metadata
1 maintainer
Release files for nnsight 0.8.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| nnsight-0.8.1.tar.gz | 770.4 kB | With provenance | Details for nnsight-0.8.1.tar.gz |
Built distributions (wheels)
Total release size: 8.2 MB
Release files / nnsight-0.8.1.tar.gz
| Download URL | nnsight-0.8.1.tar.gz |
|---|---|
| Size | 770.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0fd9bd354b202d39f1d1ae90cdd02c1112e628325878b49a600876994b210867
|
|
BLAKE2b-256 checksum How to use checksums |
30af2a496d72e601485993a419a5f607082e05bff715fe0810ea314b1006c35d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314t-win_amd64.whl
| Download URL | nnsight-0.8.1-cp314-cp314t-win_amd64.whl |
|---|---|
| Size | 308.9 kB |
| Tags | CPython 3.14 CPython 3.14 free-threading Windows x86-64 |
|
SHA-256 checksum How to use checksums |
cde68cd86c50f593b5768e4df08411af586dcc6bc3eb3ecd2312037c8b5eaa87
|
|
BLAKE2b-256 checksum How to use checksums |
857b2fd02886caf8958c61666d027f8eddb2ccac1a47d399dd07e1267ca773cd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314t-win32.whl
| Download URL | nnsight-0.8.1-cp314-cp314t-win32.whl |
|---|---|
| Size | 308.7 kB |
| Tags | CPython 3.14 CPython 3.14 free-threading Windows x86-32 |
|
SHA-256 checksum How to use checksums |
ecd01073ddffa304abadb1df9f0e4e2c4537cf975280d6b3f02c62ba7225ccd5
|
|
BLAKE2b-256 checksum How to use checksums |
87c7622a61465c541394b1d30fa282f29a97ae5df6861be579479bb2b1af5550
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
| Download URL | nnsight-0.8.1-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl |
|---|---|
| Size | 314.1 kB |
| Tags | CPython 3.14 CPython 3.14 free-threading Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
bfad66d444bcea071b5a4e8fac0d5836a6005882569e6444fb853dc790b37a41
|
|
BLAKE2b-256 checksum How to use checksums |
ded8598b4a9bbb928c23a48312f32d4118b6251343dda15f2c29fa7ce42df7d1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314t-macosx_11_0_arm64.whl
| Download URL | nnsight-0.8.1-cp314-cp314t-macosx_11_0_arm64.whl |
|---|---|
| Size | 305.8 kB |
| Tags | CPython 3.14 CPython 3.14 free-threading macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
99b0a0f6792e35a4dee39f3f111439af92a573372d7072ed19aebf7798138b7c
|
|
BLAKE2b-256 checksum How to use checksums |
0ee5b6aea7b8e7b1e226e2d001a03aa6ba1d9b56e13ebe7102e2eedbcaa7af28
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314-win_amd64.whl
| Download URL | nnsight-0.8.1-cp314-cp314-win_amd64.whl |
|---|---|
| Size | 308.9 kB |
| Tags | CPython 3.14 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
3a6e1c175f71a95e810040f0d7697c80221f87dfce27c74ae7f7e95924de4cb0
|
|
BLAKE2b-256 checksum How to use checksums |
1d125264a6110ef6823ec746af2548c54f2da9c65492f6e101b9d3d991235c5f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314-win32.whl
| Download URL | nnsight-0.8.1-cp314-cp314-win32.whl |
|---|---|
| Size | 308.6 kB |
| Tags | CPython 3.14 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
6dbe853c17223b8f3bd37464921dfb4de1df1d30d84d5c43ba7ac7a31afda321
|
|
BLAKE2b-256 checksum How to use checksums |
d7dec784a23da902cd96587ec41edf1e09c5590d07c1b02322f5f6b97671c242
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
| Download URL | nnsight-0.8.1-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl |
|---|---|
| Size | 313.3 kB |
| Tags | CPython 3.14 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
bfa3571ed0049dfe3bd3e6aaf7d15348fdc9e92738af60a65bab84c28de6b38c
|
|
BLAKE2b-256 checksum How to use checksums |
27140811b67c41922b7da0c865be0fc4efaeb0ba8c97d749e0d6f17a4b3ddac0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp314-cp314-macosx_11_0_arm64.whl
| Download URL | nnsight-0.8.1-cp314-cp314-macosx_11_0_arm64.whl |
|---|---|
| Size | 305.7 kB |
| Tags | CPython 3.14 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
260ce0d25abe7bcef13ad615e5d57227dd270a1118f1ede4abdb618f7d35a3af
|
|
BLAKE2b-256 checksum How to use checksums |
968ba6d666a941d56bcc84d69aa32c4d1bc59c4ce99335fa287e8a868e428a6b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp313-cp313-win_amd64.whl
| Download URL | nnsight-0.8.1-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 308.3 kB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
9a85a453449256137fcba617976e26adc88090a6f11f50f97e08b6632593915e
|
|
BLAKE2b-256 checksum How to use checksums |
13277d8a820a5394a2abd351e7ffbb024666340196d51ba07fc9293c97320741
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp313-cp313-win32.whl
| Download URL | nnsight-0.8.1-cp313-cp313-win32.whl |
|---|---|
| Size | 308.0 kB |
| Tags | CPython 3.13 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
f20147be73d3b939170dd1ba9aacbf53ef9173da92e9f543ccebc886e2cda0c1
|
|
BLAKE2b-256 checksum How to use checksums |
74200397c58fa9c00d0f6fd45b74ca69073d52f3153c462a9393c2b2b08480db
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
| Download URL | nnsight-0.8.1-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl |
|---|---|
| Size | 313.2 kB |
| Tags | CPython 3.13 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
61ca58aaf6119a818a0b3479bcd9cc2d2c85e041e6fed6d188be3d2d41d6724d
|
|
BLAKE2b-256 checksum How to use checksums |
cb530874ed9b86dfa67ee4606360711ed09530235ac38ff38e70100e1799502f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp313-cp313-macosx_11_0_arm64.whl
| Download URL | nnsight-0.8.1-cp313-cp313-macosx_11_0_arm64.whl |
|---|---|
| Size | 305.7 kB |
| Tags | CPython 3.13 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
1b379dd74771eb84bd4507d7506243d87d9f22fbe616c6c04bf77005e4846b07
|
|
BLAKE2b-256 checksum How to use checksums |
438079fca0d0321f1aa02b1b3e3ee83fbff30d4e14022809a78e01d716a8d375
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp312-cp312-win_amd64.whl
| Download URL | nnsight-0.8.1-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 308.3 kB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
b31bf95f1532432a83dff2e949dfae5b412000f04b552b739460ad5042c2c141
|
|
BLAKE2b-256 checksum How to use checksums |
127b3482d71548d50bfb7995bc62f8684a99903486b4dda141cd9938e154c20b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp312-cp312-win32.whl
| Download URL | nnsight-0.8.1-cp312-cp312-win32.whl |
|---|---|
| Size | 308.0 kB |
| Tags | CPython 3.12 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
f33b6b25435131511520cd4262df4b8d46bcbf079a65687f6a96002d2bb1529f
|
|
BLAKE2b-256 checksum How to use checksums |
42ddf8d046f25e42ea4450a38c321bb66ed6474a3cef963b01ad294fdb127d77
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
| Download URL | nnsight-0.8.1-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl |
|---|---|
| Size | 313.2 kB |
| Tags | CPython 3.12 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
b539d3d6f1ef698ca1d9799eff274d37947ead4127e8b3bd4e26b7246e105650
|
|
BLAKE2b-256 checksum How to use checksums |
a8aeca50a9d7088a9670dce9e0f786bb69389bd49e94e3dcbf26d1f6897b86b9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp312-cp312-macosx_11_0_arm64.whl
| Download URL | nnsight-0.8.1-cp312-cp312-macosx_11_0_arm64.whl |
|---|---|
| Size | 305.7 kB |
| Tags | CPython 3.12 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
9da71fefca3be6052a077e2dcd6356f31bb3e6532f5e7c95024a25a1db80752f
|
|
BLAKE2b-256 checksum How to use checksums |
8286df7da21a5ea63c80dbf35d11b2655ce99e20f644a53e883b9801005937fd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp311-cp311-win_amd64.whl
| Download URL | nnsight-0.8.1-cp311-cp311-win_amd64.whl |
|---|---|
| Size | 308.3 kB |
| Tags | CPython 3.11 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
279bbd91a00f71d709f3611b7cec3e457f967daa160e7d56dfe05c0f7c8e1f3f
|
|
BLAKE2b-256 checksum How to use checksums |
eabc42c709eb5ce9e31c731119c74b0e6248ac781c26a049f31b28469ee2f265
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp311-cp311-win32.whl
| Download URL | nnsight-0.8.1-cp311-cp311-win32.whl |
|---|---|
| Size | 308.0 kB |
| Tags | CPython 3.11 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
061e6f74eed1bff25b24a5cfe2925086dfafc33bd2bd9e832022737858f9c80d
|
|
BLAKE2b-256 checksum How to use checksums |
b1ac9503bdd3f523f36f9cc44e6a750c5cbda30ac8b2a4ee2c48a9c80936499f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
| Download URL | nnsight-0.8.1-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl |
|---|---|
| Size | 312.8 kB |
| Tags | CPython 3.11 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
c790214f14848908752907ba39f14e4a356489389c91777524fbc4956b04bd38
|
|
BLAKE2b-256 checksum How to use checksums |
abcda927ed4ab4b22de34b5b161354abf85a3c417c03e9c2dc833c9fbfe49efa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp311-cp311-macosx_11_0_arm64.whl
| Download URL | nnsight-0.8.1-cp311-cp311-macosx_11_0_arm64.whl |
|---|---|
| Size | 305.6 kB |
| Tags | CPython 3.11 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
9f177a722ff8b6004ccc575f35fcb7463aa3b258867cce9b19e0297627a22c40
|
|
BLAKE2b-256 checksum How to use checksums |
064e6ae0f4e5b2e67f044fe5efd603ef3c89c38ac1077c18e895d822165a9041
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp310-cp310-win_amd64.whl
| Download URL | nnsight-0.8.1-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 308.3 kB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
b3cfa4f733b0578e8a67ed03127da6d2b153079df9a20751025557f24acfb8d6
|
|
BLAKE2b-256 checksum How to use checksums |
776fad725107c1ac8fa7e98e3c288ec33cb9252c233a353fb639fbe9dd206c44
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp310-cp310-win32.whl
| Download URL | nnsight-0.8.1-cp310-cp310-win32.whl |
|---|---|
| Size | 308.0 kB |
| Tags | CPython 3.10 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
bcf7434844da450487320a906f1782d0ae6a3c97e006ee60074d5470092f1818
|
|
BLAKE2b-256 checksum How to use checksums |
daac9e8f4d6dc6718576d6f743bb516b0fb16088e29d110cd0e586938bba978e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
| Download URL | nnsight-0.8.1-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl |
|---|---|
| Size | 312.8 kB |
| Tags | CPython 3.10 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
444497326d2250d9916a855cd1e32cc1ec074c4d4be2d03dc912df81fe51cf51
|
|
BLAKE2b-256 checksum How to use checksums |
e9506d21e694b24f7a5c25fc13b4e6b4789f0345d2d794eb4c60e43c0e7d72b6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / nnsight-0.8.1-cp310-cp310-macosx_11_0_arm64.whl
| Download URL | nnsight-0.8.1-cp310-cp310-macosx_11_0_arm64.whl |
|---|---|
| Size | 305.6 kB |
| Tags | CPython 3.10 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
a1e2c20dcd8b49652654bb36d9e25c5d4d43ec92c5a14ab27363e58dc2446c4c
|
|
BLAKE2b-256 checksum How to use checksums |
44f75761cefbb0a7bb37fd07c085971440d16992c5f4d5fe0582e26e49e15f76
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logSecurity for nnsight 0.8.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 25 files in this release have been uploaded with provenance metadata.
Attestation for nnsight-0.8.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
