Skip to content

Commit 4f7b549

Browse files
authored
docs: Fix installation instructions for CUDA-specific package URLs (#1893)
<!-- .github/pull_request_template.md --> ## 📌 Description We forgot to include cuda specific suffix for `flashinfer-jit-cache` package installation instructions, this PR fixes the issue. Also update the installation guide for nightly packages, for flashinfer-python package: * first install flashinfer-python nightly from custom index, without installing dependencies (the dependencies such as torch are not available on our self-hosted index). * the install flashinfer-python's dependency from pypi ## 🔍 Related Issues <!-- Link any related issues here --> ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [ ] All tests are passing (`unittest`, etc.). ## Reviewer Notes <!-- Optional: anything you'd like reviewers to focus on, concerns, etc. -->
1 parent fdc8338 commit 4f7b549

File tree

2 files changed

+8
-4
lines changed

2 files changed

+8
-4
lines changed

README.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -58,7 +58,8 @@ pip install flashinfer-python
5858
**For faster initialization and offline usage**, install the optional packages to have most kernels pre-compiled:
5959
```bash
6060
pip install flashinfer-python flashinfer-cubin
61-
pip install flashinfer-jit-cache --index-url https://flashinfer.ai/whl/
61+
# JIT cache package (replace cu129 with your CUDA version: cu128, cu129, or cu130)
62+
pip install flashinfer-jit-cache --index-url https://flashinfer.ai/whl/cu129
6263
```
6364

6465
This eliminates compilation and downloading overhead at runtime.
@@ -103,7 +104,8 @@ Nightly builds are available for testing the latest features:
103104

104105
```bash
105106
# Core and cubin packages
106-
pip install -U --pre flashinfer-python --extra-index-url https://flashinfer.ai/whl/nightly/
107+
pip install -U --pre flashinfer-python --index-url https://flashinfer.ai/whl/nightly/ --no-deps # Install the nightly package from custom index, without installing dependencies
108+
pip install flashinfer-python # Install flashinfer-python's dependencies from PyPI
107109
pip install -U --pre flashinfer-cubin --index-url https://flashinfer.ai/whl/nightly/
108110
# JIT cache package (replace cu129 with your CUDA version: cu128, cu129, or cu130)
109111
pip install -U --pre flashinfer-jit-cache --index-url https://flashinfer.ai/whl/nightly/cu129

docs/installation.rst

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,8 @@ FlashInfer provides three packages:
3838
.. code-block:: bash
3939
4040
pip install flashinfer-python flashinfer-cubin
41-
pip install flashinfer-jit-cache --index-url https://flashinfer.ai/whl/
41+
# JIT cache package (replace cu129 with your CUDA version: cu128, cu129, or cu130)
42+
pip install flashinfer-jit-cache --index-url https://flashinfer.ai/whl/cu129
4243
4344
This eliminates compilation and downloading overhead at runtime.
4445

@@ -105,7 +106,8 @@ Nightly builds are available for testing the latest features:
105106
.. code-block:: bash
106107
107108
# Core and cubin packages
108-
pip install -U --pre flashinfer-python --extra-index-url https://flashinfer.ai/whl/nightly/
109+
pip install -U --pre flashinfer-python --index-url https://flashinfer.ai/whl/nightly/ --no-deps # Install the nightly package from custom index, without installing dependencies
110+
pip install flashinfer-python # Install flashinfer-python's dependencies from PyPI
109111
pip install -U --pre flashinfer-cubin --index-url https://flashinfer.ai/whl/nightly/
110112
# JIT cache package (replace cu129 with your CUDA version: cu128, cu129, or cu130)
111113
pip install -U --pre flashinfer-jit-cache --index-url https://flashinfer.ai/whl/nightly/cu129

0 commit comments

Comments
 (0)