From 851ccb123745df742888f4199d04277da51d5e09 Mon Sep 17 00:00:00 2001
From: Wing Lian <wing.lian@gmail.com>
Date: Sun, 9 Jun 2024 17:13:28 -0400
Subject: [PATCH] bump deepspeed for fix for grad norm compute putting tensors
 on different devices (#1699)

---
 requirements.txt | 2 +-
 setup.py         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index b5114bbf6..52f98042c 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,7 +5,7 @@ transformers==4.41.1
 tokenizers==0.19.1
 bitsandbytes==0.43.1
 accelerate==0.30.1
-deepspeed==0.14.2
+deepspeed @ git+https://github.com/microsoft/DeepSpeed.git@bc48371c5e1fb8fd70fc79285e66201dbb65679b
 pydantic==2.6.3
 addict
 fire
diff --git a/setup.py b/setup.py
index 3d1537edf..c7b4e15de 100644
--- a/setup.py
+++ b/setup.py
@@ -83,7 +83,7 @@ setup(
             "fused-dense-lib  @ git+https://github.com/Dao-AILab/flash-attention@v2.5.8#subdirectory=csrc/fused_dense_lib",
         ],
         "deepspeed": [
-            "deepspeed==0.14.2",
+            "deepspeed @ git+https://github.com/microsoft/DeepSpeed.git@bc48371c5e1fb8fd70fc79285e66201dbb65679b",
             "deepspeed-kernels",
         ],
         "mamba-ssm": [