It's find in some machine. using hf_hub::api::sync::Api to download config is not successful which will make warmup fail since attribute like max_position_embeddings could not be got. update hf-hub to the latest version could fix it

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

Cargo.lock

@@ -594,7 +594,7 @@ dependencies = [
  "semver",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -1629,7 +1629,29 @@ dependencies = [
  "reqwest 0.11.27",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
+ "tokio",
+ "ureq",
+]
+
+[[package]]
+name = "hf-hub"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "112fa2f6ad4ab815b9e1b938b4b1e437032d055e2f92ed10fd6ab2e62d02c6b6"
+dependencies = [
+ "dirs",
+ "futures",
+ "http 1.1.0",
+ "indicatif",
+ "log",
+ "native-tls",
+ "num_cpus",
+ "rand",
+ "reqwest 0.12.9",
+ "serde",
+ "serde_json",
+ "thiserror 2.0.11",
  "tokio",
  "ureq",
 ]
@@ -1811,6 +1833,22 @@ dependencies = [
  "tokio-native-tls",
 ]
 
+[[package]]
+name = "hyper-tls"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0"
+dependencies = [
+ "bytes",
+ "http-body-util",
+ "hyper 1.5.1",
+ "hyper-util",
+ "native-tls",
+ "tokio",
+ "tokio-native-tls",
+ "tower-service",
+]
+
 [[package]]
 name = "hyper-util"
 version = "0.1.10"
@@ -2085,7 +2123,7 @@ checksum = "94bd26b1b737bc11f183620072e188d1c6ede67e0e78682228d66b49ec510e17"
 dependencies = [
  "opentelemetry 0.20.0",
  "opentelemetry-otlp",
- "thiserror",
+ "thiserror 1.0.69",
  "tracing",
  "tracing-opentelemetry 0.21.0",
 ]
@@ -2421,7 +2459,7 @@ dependencies = [
  "metrics",
  "metrics-util",
  "quanta",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tracing",
 ]
@@ -2552,7 +2590,7 @@ dependencies = [
  "futures",
  "pin-project",
  "rand",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tokio-util",
  "tracing",
@@ -2601,10 +2639,10 @@ dependencies = [
  "once_cell",
  "parking_lot",
  "regex",
- "rustls-pemfile",
+ "rustls-pemfile 1.0.4",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tokio-retry",
  "tokio-util",
@@ -2908,7 +2946,7 @@ dependencies = [
  "js-sys",
  "once_cell",
  "pin-project-lite",
- "thiserror",
+ "thiserror 1.0.69",
  "urlencoding",
 ]
 
@@ -2926,7 +2964,7 @@ dependencies = [
  "opentelemetry_api",
  "opentelemetry_sdk 0.20.0",
  "prost 0.11.9",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tonic 0.9.2",
 ]
@@ -2964,7 +3002,7 @@ dependencies = [
  "js-sys",
  "once_cell",
  "pin-project-lite",
- "thiserror",
+ "thiserror 1.0.69",
  "urlencoding",
 ]
 
@@ -2986,7 +3024,7 @@ dependencies = [
  "rand",
  "regex",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tokio-stream",
 ]
@@ -3008,7 +3046,7 @@ dependencies = [
  "ordered-float 4.5.0",
  "percent-encoding",
  "rand",
- "thiserror",
+ "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -3545,7 +3583,7 @@ dependencies = [
  "rand_chacha",
  "simd_helpers",
  "system-deps",
- "thiserror",
+ "thiserror 1.0.69",
  "v_frame",
  "wasm-bindgen",
 ]
@@ -3622,7 +3660,7 @@ checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
 dependencies = [
  "getrandom",
  "libredox",
- "thiserror",
+ "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -3717,7 +3755,7 @@ dependencies = [
  "http 0.2.12",
  "http-body 0.4.6",
  "hyper 0.14.31",
- "hyper-tls",
+ "hyper-tls 0.5.0",
  "ipnet",
  "js-sys",
  "log",
@@ -3726,12 +3764,12 @@ dependencies = [
  "once_cell",
  "percent-encoding",
  "pin-project-lite",
- "rustls-pemfile",
+ "rustls-pemfile 1.0.4",
  "serde",
  "serde_json",
  "serde_urlencoded",
  "sync_wrapper 0.1.2",
- "system-configuration",
+ "system-configuration 0.5.1",
  "tokio",
  "tokio-native-tls",
  "tower-service",
@@ -3750,30 +3788,40 @@ checksum = "a77c62af46e79de0a562e1a9849205ffcb7fc1238876e9bd743357570e04046f"
 dependencies = [
  "base64 0.22.1",
  "bytes",
+ "encoding_rs",
  "futures-channel",
  "futures-core",
  "futures-util",
+ "h2 0.4.7",
  "http 1.1.0",
  "http-body 1.0.1",
  "http-body-util",
  "hyper 1.5.1",
+ "hyper-rustls",
+ "hyper-tls 0.6.0",
  "hyper-util",
  "ipnet",
  "js-sys",
  "log",
  "mime",
+ "native-tls",
  "once_cell",
  "percent-encoding",
  "pin-project-lite",
+ "rustls-pemfile 2.2.0",
  "serde",
  "serde_json",
  "serde_urlencoded",
  "sync_wrapper 1.0.2",
+ "system-configuration 0.6.1",
  "tokio",
+ "tokio-native-tls",
+ "tokio-util",
  "tower-service",
  "url",
  "wasm-bindgen",
  "wasm-bindgen-futures",
+ "wasm-streams",
  "web-sys",
  "windows-registry",
 ]
@@ -3944,6 +3992,15 @@ dependencies = [
  "base64 0.21.7",
 ]
 
+[[package]]
+name = "rustls-pemfile"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dce314e5fee3f39953d46bb63bb8a46d40c2f8fb7cc5a3b6cab2bde9721d6e50"
+dependencies = [
+ "rustls-pki-types",
+]
+
 [[package]]
 name = "rustls-pki-types"
 version = "1.10.0"
@@ -4254,6 +4311,17 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "socks"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0c3dbbd9ae980613c6dd8e28a9407b50509d3803b57624d5dfe8315218cd58b"
+dependencies = [
+ "byteorder",
+ "libc",
+ "winapi",
+]
+
 [[package]]
 name = "spin"
 version = "0.5.2"
@@ -4395,7 +4463,18 @@ checksum = "ba3a3adc5c275d719af8cb4272ea1c4a6d668a777f37e115f6d11ddbc1c8e0e7"
 dependencies = [
  "bitflags 1.3.2",
  "core-foundation 0.9.4",
- "system-configuration-sys",
+ "system-configuration-sys 0.5.0",
+]
+
+[[package]]
+name = "system-configuration"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3c879d448e9d986b661742763247d3693ed13609438cf3d006f51f5368a5ba6b"
+dependencies = [
+ "bitflags 2.6.0",
+ "core-foundation 0.9.4",
+ "system-configuration-sys 0.6.0",
 ]
 
 [[package]]
@@ -4408,6 +4487,16 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "system-configuration-sys"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e1d1b10ced5ca923a1fcb8d03e96b8d3268065d724548c0211415ff6ac6bac4"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
 [[package]]
 name = "system-deps"
 version = "6.2.2"
@@ -4483,11 +4572,11 @@ dependencies = [
  "cxx",
  "cxx-build",
  "hashbrown 0.15.1",
- "hf-hub",
+ "hf-hub 0.3.2",
  "pkg-config",
  "pyo3",
  "text-generation-router",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4501,13 +4590,13 @@ dependencies = [
  "average",
  "clap 4.5.21",
  "float-ord",
- "hf-hub",
+ "hf-hub 0.3.2",
  "ratatui",
  "serde",
  "serde_json",
  "tabled",
  "text-generation-client",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tracing",
@@ -4524,7 +4613,7 @@ dependencies = [
  "grpc-metadata",
  "prost 0.12.6",
  "prost-build",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tonic 0.10.2",
  "tonic-build",
@@ -4539,7 +4628,7 @@ dependencies = [
  "clap 4.5.21",
  "ctrlc",
  "float_eq",
- "hf-hub",
+ "hf-hub 0.4.1",
  "nix 0.28.0",
  "once_cell",
  "pyo3",
@@ -4547,7 +4636,7 @@ dependencies = [
  "reqwest 0.11.27",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tracing",
  "tracing-subscriber",
  "vergen",
@@ -4568,7 +4657,7 @@ dependencies = [
  "csv",
  "futures",
  "futures-util",
- "hf-hub",
+ "hf-hub 0.3.2",
  "image",
  "init-tracing-opentelemetry",
  "itertools 0.10.5",
@@ -4590,7 +4679,7 @@ dependencies = [
  "serde",
  "serde_json",
  "sysinfo",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4618,7 +4707,7 @@ dependencies = [
  "futures",
  "futures-util",
  "grpc-metadata",
- "hf-hub",
+ "hf-hub 0.3.2",
  "image",
  "init-tracing-opentelemetry",
  "jsonschema",
@@ -4639,7 +4728,7 @@ dependencies = [
  "serde_json",
  "slotmap",
  "text-generation-router",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4668,7 +4757,7 @@ dependencies = [
  "futures",
  "futures-util",
  "grpc-metadata",
- "hf-hub",
+ "hf-hub 0.3.2",
  "image",
  "init-tracing-opentelemetry",
  "itertools 0.13.0",
@@ -4690,7 +4779,7 @@ dependencies = [
  "serde_json",
  "slotmap",
  "text-generation-router",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4720,7 +4809,16 @@ version = "1.0.69"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 1.0.69",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d452f284b73e6d76dd36758a0c8684b1d5be31f92b89d07fd5822175732206fc"
+dependencies = [
+ "thiserror-impl 2.0.11",
 ]
 
 [[package]]
@@ -4734,6 +4832,17 @@ dependencies = [
  "syn 2.0.89",
 ]
 
+[[package]]
+name = "thiserror-impl"
+version = "2.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26afc1baea8a989337eeb52b6e72a039780ce45c3edfcc9c5b9d112feeb173c2"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.89",
+]
+
 [[package]]
 name = "thread_local"
 version = "1.1.8"
@@ -4818,7 +4927,7 @@ dependencies = [
  "derive_builder",
  "esaxx-rs",
  "getrandom",
- "hf-hub",
+ "hf-hub 0.3.2",
  "indicatif",
  "itertools 0.12.1",
  "lazy_static",
@@ -4835,7 +4944,7 @@ dependencies = [
  "serde",
  "serde_json",
  "spm_precompiled",
- "thiserror",
+ "thiserror 1.0.69",
  "unicode-normalization-alignments",
  "unicode-segmentation",
  "unicode_categories",
@@ -5337,6 +5446,7 @@ dependencies = [
  "rustls-webpki",
  "serde",
  "serde_json",
+ "socks",
  "url",
  "webpki-roots",
 ]
@@ -5599,6 +5709,19 @@ version = "0.2.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "65fc09f10666a9f147042251e0dda9c18f166ff7de300607007e96bdebc1068d"
 
+[[package]]
+name = "wasm-streams"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "15053d8d85c7eccdbefef60f06769760a563c7f0a9d6902a13d35c7800b0ad65"
+dependencies = [
+ "futures-util",
+ "js-sys",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
 [[package]]
 name = "web-sys"
 version = "0.3.72"

Dockerfile_intel

@@ -162,7 +162,7 @@ ARG MAMBA_VERSION=23.1.0-1
 ARG PYTHON_VERSION='3.11.10'
 # Automatically set by buildx
 ARG TARGETPLATFORM
-ENV PATH /opt/conda/bin:$PATH
+ENV PATH=/opt/conda/bin:$PATH
 
 # TGI seem to require libssl.so.1.1 instead of libssl.so.3 so we can't use ubuntu 22.04. Ubuntu 20.04 has python==3.8, and TGI requires python>=3.9, hence the need for miniconda.
 # Install mamba

launcher/Cargo.toml

@@ -9,7 +9,7 @@ homepage.workspace = true
 [dependencies]
 clap = { version = "4.4.5", features = ["derive", "env"] }
 ctrlc = { version = "3.4.1", features = ["termination"] }
-hf-hub = "0.3.2"
+hf-hub = "0.4.1"
 nix = { version = "0.28.0", features = ["signal"] }
 once_cell = "1.19.0"
 pyo3 = { workspace = true }