flashinfer-python 0.2.12__tar.gz → 0.2.14__tar.gz

flashinfer_python-0.2.14/LICENSE

@@ -0,0 +1,229 @@
+                                 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.
+
+-------------------------------------------------------------------------------------------------
+Some of the code in this project are adapted from other open-source projects with different
+licenses. This product also bundles some third-party components under other open source licenses.
+This section summarizes those components and their licenses.
+See licenses/ for text of these licenses.
+
+BSD 3-Clause License
+--------------------
+
+include/flashinfer/attention/hopper/epilogue.cuh
+include/flashinfer/attention/hopper/mainloop.cuh
+include/flashinfer/attention/hopper/kernel_traits.cuh
+include/flashinfer/attention/hopper/named_barrier.cuh
+include/flashinfer/attention/hopper/tile_scheduler.cuh
+include/flashinfer/attention/hopper/utils.cuh
+
+BSD 3-Clause "New" License
+--------------------------
+
+3rdparty/cutlass
+include/flashinfer/attention/hopper/block_sparse_gather.cuh
+
+MIT License
+-----------
+
+3rdparty/spdlog
+3rdparty/spdlog/include/spdlog/fmt/bundled (fmt library)

flashinfer_python-0.2.14/PKG-INFO

@@ -0,0 +1,194 @@
+Metadata-Version: 2.4
+Name: flashinfer-python
+Version: 0.2.14
+Summary: FlashInfer: Kernel Library for LLM Serving
+Author: FlashInfer team
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/flashinfer-ai/flashinfer
+Requires-Python: <4.0,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: licenses/LICENSE.cutlass.txt
+License-File: licenses/LICENSE.flashattention3.txt
+License-File: licenses/LICENSE.fmt.txt
+License-File: licenses/LICENSE.spdlog.txt
+Requires-Dist: numpy
+Requires-Dist: torch
+Requires-Dist: ninja
+Requires-Dist: requests
+Requires-Dist: cuda-python<=12.9
+Requires-Dist: pynvml
+Requires-Dist: einops
+Requires-Dist: packaging>=24.2
+Requires-Dist: nvidia-cudnn-frontend>=1.13.0
+Dynamic: license-file
+Dynamic: requires-dist
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://github.com/flashinfer-ai/web-data/blob/main/logo/FlashInfer-black-background.png?raw=true">
+    <img alt="FlashInfer" src="https://github.com/flashinfer-ai/web-data/blob/main/logo/FlashInfer-white-background.png?raw=true" width=55%>
+  </picture>
+</p>
+<h1 align="center">
+Kernel Library for LLM Serving
+</h1>
+
+<p align="center">
+| <a href="https://flashinfer.ai"><b>Blog</b></a> | <a href="https://docs.flashinfer.ai"><b>Documentation</b></a> | <a href="https://join.slack.com/t/flashinfer/shared_invite/zt-379wct3hc-D5jR~1ZKQcU00WHsXhgvtA"><b>Slack</b></a> |  <a href="https://github.com/orgs/flashinfer-ai/discussions"><b>Discussion Forum</b></a> |
+</p>
+
+[![Build Status](https://ci.tlcpack.ai/job/flashinfer-ci/job/main/badge/icon)](https://ci.tlcpack.ai/job/flashinfer-ci/job/main/)
+[![Release](https://github.com/flashinfer-ai/flashinfer/actions/workflows/release_wheel.yml/badge.svg)](https://github.com/flashinfer-ai/flashinfer/actions/workflows/release_wheel.yml)
+[![Documentation](https://github.com/flashinfer-ai/flashinfer/actions/workflows/build-doc.yml/badge.svg)](https://github.com/flashinfer-ai/flashinfer/actions/workflows/build-doc.yml)
+
+
+FlashInfer is a library and kernel generator for Large Language Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, SparseAttention, PageAttention, Sampling, and more. FlashInfer focuses on LLM serving and inference, and delivers state-of-the-art performance across diverse scenarios.
+
+Check our [v0.2 release blog](https://flashinfer.ai/2024/12/16/flashinfer-v02-release.html) for new features!
+
+The core features of FlashInfer include:
+1. **Efficient Sparse/Dense Attention Kernels**: Efficient single/batch attention for sparse(paged)/dense KV-storage on CUDA Cores and Tensor Cores (both FA2 & FA3) templates. The vector-sparse attention can achieve 90% of the bandwidth of dense kernels with same problem size.
+2. **Load-Balanced Scheduling**: FlashInfer decouples `plan`/`run` stage of attention computation where we schedule the computation of variable-length inputs in `plan` stage to alleviate load-imbalance issue.
+3. **Memory Efficiency**: FlashInfer offers [Cascade Attention](https://docs.flashinfer.ai/api/cascade.html#flashinfer.cascade.MultiLevelCascadeAttentionWrapper) for hierarchical KV-Cache, and implements Head-Query fusion for accelerating Grouped-Query Attention, and efficient kernels for low-precision attention and fused-RoPE attention for compressed KV-Cache.
+4. **Customizable Attention**: Bring your own attention variants through JIT-compilation.
+5. **CUDAGraph and torch.compile Compatibility**: FlashInfer kernels can be captured by CUDAGraphs and torch.compile for low-latency inference.
+6. **Efficient LLM-specific Operators**: High-Performance [fused kernel for Top-P, Top-K/Min-P sampling](https://docs.flashinfer.ai/api/sampling.html) without the need to sorting.
+
+FlashInfer supports PyTorch, TVM and C++ (header-only) APIs, and can be easily integrated into existing projects.
+
+## News
+- [Mar 10, 2025] [Blog Post](https://flashinfer.ai/2025/03/10/sampling.html) Sorting-Free GPU Kernels for LLM Sampling, which explains the design of sampling kernels in FlashInfer.
+- [Mar 1, 2025] Checkout flashinfer's [intra-kernel profiler](https://github.com/flashinfer-ai/flashinfer/tree/main/profiler) for visualizing the timeline of each threadblock in GPU kernels.
+- [Dec 16, 2024] [Blog Post](https://flashinfer.ai/2024/12/16/flashinfer-v02-release.html) FlashInfer 0.2 - Efficient and Customizable Kernels for LLM Inference Serving
+- [Sept 2024] We've launched a [Slack](https://join.slack.com/t/flashinfer/shared_invite/zt-2r93kj2aq-wZnC2n_Z2~mf73N5qnVGGA) workspace for Flashinfer users and developers. Join us for timely support, discussions, updates and knowledge sharing!
+- [Jan 31, 2024] [Blog Post](https://flashinfer.ai/2024/01/08/cascade-inference.html) Cascade Inference: Memory-Efficient Shared Prefix Batch Decoding
+- [Jan 31, 2024] [Blog Post](https://flashinfer.ai/2024/01/03/introduce-flashinfer.html) Accelerating Self-Attentions for LLM Serving with FlashInfer
+
+## Getting Started
+
+Using our PyTorch API is the easiest way to get started:
+
+### Install from PIP
+
+FlashInfer is available as a Python package for Linux on PyPI. You can install it with the following command:
+
+```bash
+pip install flashinfer-python
+```
+
+### Install from Source
+
+Alternatively, build FlashInfer from source:
+
+```bash
+git clone https://github.com/flashinfer-ai/flashinfer.git --recursive
+cd flashinfer
+python -m pip install -v .
+
+# for development & contribution, install in editable mode
+python -m pip install --no-build-isolation -e . -v
+```
+
+To pre-compile essential kernels ahead-of-time (AOT), run the following command:
+
+```bash
+# Set target CUDA architectures
+export TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a"
+# Build AOT kernels. Will produce AOT kernels in aot-ops/
+python -m flashinfer.aot
+# Build AOT wheel
+python -m build --no-isolation --wheel
+# Install AOT wheel
+python -m pip install dist/flashinfer_*.whl
+```
+
+For more details, refer to the [Install from Source documentation](https://docs.flashinfer.ai/installation.html#install-from-source).
+
+### Trying it out
+
+Below is a minimal example of using FlashInfer's single-request decode/append/prefill attention kernels:
+
+```python
+import torch
+import flashinfer
+
+kv_len = 2048
+num_kv_heads = 32
+head_dim = 128
+
+k = torch.randn(kv_len, num_kv_heads, head_dim).half().to(0)
+v = torch.randn(kv_len, num_kv_heads, head_dim).half().to(0)
+
+# decode attention
+
+num_qo_heads = 32
+q = torch.randn(num_qo_heads, head_dim).half().to(0)
+
+o = flashinfer.single_decode_with_kv_cache(q, k, v) # decode attention without RoPE on-the-fly
+o_rope_on_the_fly = flashinfer.single_decode_with_kv_cache(q, k, v, pos_encoding_mode="ROPE_LLAMA") # decode with LLaMA style RoPE on-the-fly
+
+# append attention
+append_qo_len = 128
+q = torch.randn(append_qo_len, num_qo_heads, head_dim).half().to(0) # append attention, the last 128 tokens in the KV-Cache are the new tokens
+o = flashinfer.single_prefill_with_kv_cache(q, k, v, causal=True) # append attention without RoPE on-the-fly, apply causal mask
+o_rope_on_the_fly = flashinfer.single_prefill_with_kv_cache(q, k, v, causal=True, pos_encoding_mode="ROPE_LLAMA") # append attention with LLaMA style RoPE on-the-fly, apply causal mask
+
+# prefill attention
+qo_len = 2048
+q = torch.randn(qo_len, num_qo_heads, head_dim).half().to(0) # prefill attention
+o = flashinfer.single_prefill_with_kv_cache(q, k, v, causal=False) # prefill attention without RoPE on-the-fly, do not apply causal mask
+```
+
+Check out [documentation](https://docs.flashinfer.ai/) for usage of batch decode/append/prefill kernels and shared-prefix cascading kernels.
+
+## Custom Attention Variants
+
+Starting from FlashInfer v0.2, users can customize their own attention variants with additional parameters. For more details, refer to our [JIT examples](https://github.com/flashinfer-ai/flashinfer/blob/main/tests/test_jit_example.py).
+
+## C++ API and TVM Bindings
+
+FlashInfer also provides C++ API and TVM bindings, please refer to [documentation](https://docs.flashinfer.ai/) for more details.
+
+## Adoption
+
+We are thrilled to share that FlashInfer is being adopted by many cutting-edge projects, including but not limited to:
+- [MLC-LLM](https://github.com/mlc-ai/mlc-llm)
+- [Punica](https://github.com/punica-ai/punica)
+- [SGLang](https://github.com/sgl-project/sglang)
+- [ScaleLLM](https://github.com/vectorch-ai/ScaleLLM)
+- [vLLM](https://github.com/vllm-project/vllm)
+- [TGI](https://github.com/huggingface/text-generation-inference)
+- [lorax](https://github.com/predibase/lorax)
+- [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM)
+- [LightLLM](https://github.com/ModelTC/lightllm)
+
+## Acknowledgement
+
+FlashInfer is inspired by [FlashAttention 1&2](https://github.com/dao-AILab/flash-attention/), [vLLM](https://github.com/vllm-project/vllm), [stream-K](https://arxiv.org/abs/2301.03598), [cutlass](https://github.com/nvidia/cutlass) and [AITemplate](https://github.com/facebookincubator/AITemplate) projects.
+
+## Citation
+
+If you find FlashInfer helpful in your project or research, please consider citing our [paper](https://arxiv.org/abs/2501.01005):
+
+```bibtex
+@article{ye2025flashinfer,
+    title = {FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving},
+    author = {
+      Ye, Zihao and
+      Chen, Lequn and
+      Lai, Ruihang and
+      Lin, Wuwei and
+      Zhang, Yineng and
+      Wang, Stephanie and
+      Chen, Tianqi and
+      Kasikci, Baris and
+      Grover, Vinod and
+      Krishnamurthy, Arvind and
+      Ceze, Luis
+    },
+    journal = {arXiv preprint arXiv:2501.01005},
+    year = {2025},
+    url = {https://arxiv.org/abs/2501.01005}
+}
+```