From 564bdf29f7ef630f4ff8cd32afa5c070e99e67f0 Mon Sep 17 00:00:00 2001
From: Yineng Zhang <me@zhyncs.com>
Date: Thu, 27 Feb 2025 09:53:48 -0800
Subject: [PATCH] upgrade flashinfer v0.2.2.post1 (#3934)

---
 docs/start/install.md                   | 2 +-
 python/pyproject.toml                   | 2 +-
 python/sglang/srt/entrypoints/engine.py | 2 +-
 scripts/ci_install_dependency.sh        | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/docs/start/install.md b/docs/start/install.md
index 9dc26bfd7..55b084d38 100644
--- a/docs/start/install.md
+++ b/docs/start/install.md
@@ -143,4 +143,4 @@ sky status --endpoint 30000 sglang
 - [FlashInfer](https://github.com/flashinfer-ai/flashinfer) is the default attention kernel backend. It only supports sm75 and above. If you encounter any FlashInfer-related issues on sm75+ devices (e.g., T4, A10, A100, L4, L40S, H100), please switch to other kernels by adding `--attention-backend triton --sampling-backend pytorch` and open an issue on GitHub.
 - If you only need to use OpenAI models with the frontend language, you can avoid installing other dependencies by using `pip install "sglang[openai]"`.
 - The language frontend operates independently of the backend runtime. You can install the frontend locally without needing a GPU, while the backend can be set up on a GPU-enabled machine. To install the frontend, run `pip install sglang`, and for the backend, use `pip install sglang[srt]`. `srt` is the abbreviation of SGLang runtime.
-- To reinstall flashinfer locally, use the following command: `pip install "flashinfer-python>=0.2.1.post2" -i https://flashinfer.ai/whl/cu124/torch2.5 --force-reinstall --no-deps` and then delete the cache with `rm -rf ~/.cache/flashinfer`.
+- To reinstall flashinfer locally, use the following command: `pip install "flashinfer-python>=0.2.2.post1" -i https://flashinfer.ai/whl/cu124/torch2.5 --force-reinstall --no-deps` and then delete the cache with `rm -rf ~/.cache/flashinfer`.
diff --git a/python/pyproject.toml b/python/pyproject.toml
index 395108c41..1c762bbcb 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -43,7 +43,7 @@ runtime_common = [
 srt = [
     "sglang[runtime_common]",
     "sgl-kernel>=0.0.3.post6",
-    "flashinfer_python>=0.2.1.post2",
+    "flashinfer_python>=0.2.2.post1",
     "torch==2.5.1",
     "vllm>=0.6.4.post1,<=0.7.2",
     "cuda-python",
diff --git a/python/sglang/srt/entrypoints/engine.py b/python/sglang/srt/entrypoints/engine.py
index 1fb2f7c64..671b8f2c3 100644
--- a/python/sglang/srt/entrypoints/engine.py
+++ b/python/sglang/srt/entrypoints/engine.py
@@ -330,7 +330,7 @@ def _set_envs_and_config(server_args: ServerArgs):
     if server_args.attention_backend == "flashinfer":
         assert_pkg_version(
             "flashinfer_python",
-            "0.2.1.post2",
+            "0.2.2.post1",
             "Please uninstall the old version and "
             "reinstall the latest version by following the instructions "
             "at https://docs.flashinfer.ai/installation.html.",
diff --git a/scripts/ci_install_dependency.sh b/scripts/ci_install_dependency.sh
index d5c09751b..b496ac787 100755
--- a/scripts/ci_install_dependency.sh
+++ b/scripts/ci_install_dependency.sh
@@ -16,7 +16,7 @@ pip install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2
 
 rm -rf /root/.cache/flashinfer
 # Force reinstall flashinfer and torch_memory_saver
-pip install flashinfer_python==0.2.1.post2 --find-links ${FLASHINFER_REPO} --force-reinstall --no-deps
+pip install flashinfer_python==0.2.2.post1 --find-links ${FLASHINFER_REPO} --force-reinstall --no-deps
 
 pip install torch_memory_saver --force-reinstall