diff --git a/Cargo.lock b/Cargo.lock
index 31afeda9b..2e75fe8fc 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -310,9 +310,9 @@ dependencies = [
 
 [[package]]
 name = "base64"
-version = "0.22.1"
+version = "0.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8"
 
 [[package]]
 name = "base64"
@@ -3552,7 +3552,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "2.0.2"
+version = "2.0.4"
 dependencies = [
  "average",
  "clap",
@@ -3573,7 +3573,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "2.0.2"
+version = "2.0.4"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -3590,7 +3590,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "2.0.2"
+version = "2.0.4"
 dependencies = [
  "clap",
  "ctrlc",
@@ -3609,7 +3609,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "2.0.2"
+version = "2.0.4"
 dependencies = [
  "async-stream",
  "axum",
diff --git a/Cargo.toml b/Cargo.toml
index 34e55652d..aafc8435b 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -9,7 +9,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "2.0.2"
+version = "2.0.4"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/Dockerfile b/Dockerfile
index 73a274dc0..af3fa4a56 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -74,5 +74,5 @@ COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/
 # Final image
 FROM base
 
-ENTRYPOINT ["text-generation-launcher"]
-CMD ["--json-output"]
+#ENTRYPOINT ["text-generation-launcher"]
+#CMD ["--json-output"]
diff --git a/server/pyproject.toml b/server/pyproject.toml
index c91e88499..5b6f720a6 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "2.0.2"
+version = "2.0.4"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]
 
diff --git a/server/requirements_cuda.txt b/server/requirements_cuda.txt
index 9035f6bc4..88fcc4f36 100644
--- a/server/requirements_cuda.txt
+++ b/server/requirements_cuda.txt
@@ -6,14 +6,14 @@ colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_p
 deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
 einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
 filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13"
-fsspec==2024.3.1 ; python_version >= "3.9" and python_version < "3.13"
+fsspec==2024.5.0 ; python_version >= "3.9" and python_version < "3.13"
 googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
 grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
 grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
 grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
-grpcio==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
+grpcio==1.64.0 ; python_version >= "3.9" and python_version < "3.13"
 hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
-huggingface-hub==0.23.0 ; python_version >= "3.9" and python_version < "3.13"
+huggingface-hub==0.23.1 ; python_version >= "3.9" and python_version < "3.13"
 idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
 loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
 numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
@@ -32,17 +32,17 @@ prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
 protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13"
 py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
 pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
-regex==2024.5.10 ; python_version >= "3.9" and python_version < "3.13"
-requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13"
+regex==2024.5.15 ; python_version >= "3.9" and python_version < "3.13"
+requests==2.32.2 ; python_version >= "3.9" and python_version < "3.13"
 safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13"
-scipy==1.13.0 ; python_version >= "3.9" and python_version < "3.13"
+scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
 sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
-setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13"
+setuptools==70.0.0 ; python_version >= "3.9" and python_version < "3.13"
 tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
 tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
-transformers @ git+https://github.com/huggingface/transformers.git@b8aee2e918d7ba2d5e9e80162ae26b4806873307 ; python_version >= "3.9" and python_version < "3.13"
+transformers==4.41.1 ; python_version >= "3.9" and python_version < "3.13"
 typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
-typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13"
+typing-extensions==4.12.0 ; python_version >= "3.9" and python_version < "3.13"
 urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
 win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
 wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
diff --git a/server/requirements_rocm.txt b/server/requirements_rocm.txt
index 9035f6bc4..88fcc4f36 100644
--- a/server/requirements_rocm.txt
+++ b/server/requirements_rocm.txt
@@ -6,14 +6,14 @@ colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_p
 deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
 einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
 filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13"
-fsspec==2024.3.1 ; python_version >= "3.9" and python_version < "3.13"
+fsspec==2024.5.0 ; python_version >= "3.9" and python_version < "3.13"
 googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
 grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
 grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
 grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
-grpcio==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
+grpcio==1.64.0 ; python_version >= "3.9" and python_version < "3.13"
 hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
-huggingface-hub==0.23.0 ; python_version >= "3.9" and python_version < "3.13"
+huggingface-hub==0.23.1 ; python_version >= "3.9" and python_version < "3.13"
 idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
 loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
 numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
@@ -32,17 +32,17 @@ prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
 protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13"
 py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
 pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
-regex==2024.5.10 ; python_version >= "3.9" and python_version < "3.13"
-requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13"
+regex==2024.5.15 ; python_version >= "3.9" and python_version < "3.13"
+requests==2.32.2 ; python_version >= "3.9" and python_version < "3.13"
 safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13"
-scipy==1.13.0 ; python_version >= "3.9" and python_version < "3.13"
+scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
 sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
-setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13"
+setuptools==70.0.0 ; python_version >= "3.9" and python_version < "3.13"
 tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
 tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
-transformers @ git+https://github.com/huggingface/transformers.git@b8aee2e918d7ba2d5e9e80162ae26b4806873307 ; python_version >= "3.9" and python_version < "3.13"
+transformers==4.41.1 ; python_version >= "3.9" and python_version < "3.13"
 typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
-typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13"
+typing-extensions==4.12.0 ; python_version >= "3.9" and python_version < "3.13"
 urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
 win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
 wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"