From e28a809004620c3f3a1cc28d4bbc0b4775b1328f Mon Sep 17 00:00:00 2001
From: OlivierDehaene <olivier@huggingface.co>
Date: Sat, 1 Jul 2023 19:25:41 +0200
Subject: [PATCH] v0.9.0 (#525)

---
 Cargo.lock                      | 505 ++++++++++++++++++++------------
 Cargo.toml                      |   2 +-
 Dockerfile                      |   2 +-
 README.md                       |   2 +-
 aml/README.md                   |  15 -
 aml/deployment.yaml             |  38 ---
 aml/endpoint.yaml               |   3 -
 aml/model.yaml                  |   3 -
 docs/openapi.json               |  31 +-
 launcher/src/main.rs            |   8 +-
 router/Cargo.toml               |  10 +-
 router/client/Cargo.toml        |   4 +-
 router/grpc-metadata/Cargo.toml |   6 +-
 router/src/server.rs            |   1 +
 rust-toolchain.toml             |   2 +-
 server/pyproject.toml           |   2 +-
 16 files changed, 376 insertions(+), 258 deletions(-)
 delete mode 100644 aml/README.md
 delete mode 100644 aml/deployment.yaml
 delete mode 100644 aml/endpoint.yaml
 delete mode 100644 aml/model.yaml

diff --git a/Cargo.lock b/Cargo.lock
index 7a6f4ad2..b65045ff 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "addr2line"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f4fa78e18c64fce05e902adecd7a5eed15a5e0a3439f7b0e169f0252214865e3"
+dependencies = [
+ "gimli",
+]
+
 [[package]]
 name = "adler"
 version = "1.0.2"
@@ -10,9 +19,9 @@ checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
 [[package]]
 name = "aes"
-version = "0.8.2"
+version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "433cfd6710c9986c576a25ca913c39d66a6474107b406f34f91d4a8923395241"
+checksum = "ac1f845298e95f983ff1944b728ae08b8cebab80d684f0a832ed0fc74dfa27e2"
 dependencies = [
  "cfg-if",
  "cipher",
@@ -21,11 +30,11 @@ dependencies = [
 
 [[package]]
 name = "ahash"
-version = "0.7.6"
+version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fcb51a0695d8f838b1ee009b3fbf66bda078cd64590202a864a8f3e8c4315c47"
+checksum = "2c99f64d1e06488f620f932677e24bc6e2897582980441ae90a671415bd7ec2f"
 dependencies = [
- "getrandom",
+ "cfg-if",
  "once_cell",
  "version_check",
 ]
@@ -65,15 +74,15 @@ dependencies = [
 
 [[package]]
 name = "anstyle"
-version = "1.0.0"
+version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41ed9a86bf92ae6580e0a31281f65a1b1d867c0cc68d5346e2ae128dddfa6a7d"
+checksum = "3a30da5c5f2d5e72842e00bcb57657162cdabef0931f40e2deb9b4140440cecd"
 
 [[package]]
 name = "anstyle-parse"
-version = "0.2.0"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e765fd216e48e067936442276d1d57399e37bce53c264d6fefbe298080cb57ee"
+checksum = "938874ff5980b03a87c5524b3ae5b59cf99b1d6bc836848df7bc5ada9643c333"
 dependencies = [
  "utf8parse",
 ]
@@ -139,7 +148,7 @@ checksum = "16e62a023e7c117e27523144c5d2459f4397fcc3cab0085af8e2224f643a0193"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -150,7 +159,7 @@ checksum = "b9ccdd8f2a161be9bd5c023df56f1b2a0bd1d83872ae53b71a84a12c9bf6e842"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -190,7 +199,7 @@ checksum = "f8175979259124331c1d7bf6586ee7e0da434155e4b2d48ec2c8386281d8df39"
 dependencies = [
  "async-trait",
  "axum-core",
- "bitflags",
+ "bitflags 1.3.2",
  "bytes",
  "futures-util",
  "http",
@@ -240,11 +249,26 @@ dependencies = [
  "axum",
  "futures",
  "http",
- "opentelemetry",
+ "opentelemetry 0.18.0",
  "tower",
  "tower-http 0.3.5",
  "tracing",
- "tracing-opentelemetry",
+ "tracing-opentelemetry 0.18.0",
+]
+
+[[package]]
+name = "backtrace"
+version = "0.3.68"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4319208da049c43661739c5fade2ba182f09d1dc2299b32298d3a31692b17e12"
+dependencies = [
+ "addr2line",
+ "cc",
+ "cfg-if",
+ "libc",
+ "miniz_oxide",
+ "object",
+ "rustc-demangle",
 ]
 
 [[package]]
@@ -271,6 +295,12 @@ version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
+[[package]]
+name = "bitflags"
+version = "2.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "630be753d4e58660abd17930c71b647fe46c27ea6b63cc59e1e3851406972e42"
+
 [[package]]
 name = "block-buffer"
 version = "0.10.4"
@@ -380,9 +410,9 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.3.4"
+version = "4.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "80672091db20273a15cf9fdd4e47ed43b5091ec9841bf4c6145c9dfbbcae09ed"
+checksum = "384e169cc618c613d5e3ca6404dda77a8685a63e08660dcc64abaf7da7cb0c7a"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -391,13 +421,12 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.3.4"
+version = "4.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c1458a1df40e1e2afebb7ab60ce55c1fa8f431146205aa5f4887e0b111c27636"
+checksum = "ef137bbe35aab78bdb468ccfba75a5f4d8321ae011d34063770780545176af2d"
 dependencies = [
  "anstream",
  "anstyle",
- "bitflags",
  "clap_lex",
  "strsim",
 ]
@@ -411,7 +440,7 @@ dependencies = [
  "heck",
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -528,7 +557,7 @@ version = "0.26.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a84cda67535339806297f1b331d6dd6320470d2a0fe65381e79ee9e156dd3d13"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "crossterm_winapi",
  "libc",
  "mio",
@@ -609,7 +638,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "907076dfda823b0b36d2a1bb5f90c96660a5bbcd7729e10727f07858f22c4edc"
 dependencies = [
  "cfg-if",
- "hashbrown",
+ "hashbrown 0.12.3",
  "lock_api",
  "once_cell",
  "parking_lot_core",
@@ -895,7 +924,7 @@ checksum = "89ca545a94061b6365f2c7355b4b32bd20df3ff95f02da9329b34ccc3bd6ee72"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -956,10 +985,16 @@ dependencies = [
  "cfg-if",
  "js-sys",
  "libc",
- "wasi 0.11.0+wasi-snapshot-preview1",
+ "wasi",
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "gimli"
+version = "0.27.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6c80984affa11d98d1b88b66ac8853f143217b399d3c74116778ff8fdb4ed2e"
+
 [[package]]
 name = "glob"
 version = "0.3.1"
@@ -970,17 +1005,17 @@ checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
 name = "grpc-metadata"
 version = "0.1.0"
 dependencies = [
- "opentelemetry",
- "tonic",
+ "opentelemetry 0.19.0",
+ "tonic 0.9.2",
  "tracing",
- "tracing-opentelemetry",
+ "tracing-opentelemetry 0.19.0",
 ]
 
 [[package]]
 name = "h2"
-version = "0.3.19"
+version = "0.3.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d357c7ae988e7d2182f7d7871d0b963962420b0678b0997ce7de72001aeab782"
+checksum = "97ec8491ebaf99c8eaa73058b045fe58073cd6be7f596ac993ced0b0a0c01049"
 dependencies = [
  "bytes",
  "fnv",
@@ -1000,6 +1035,12 @@ name = "hashbrown"
 version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
+
+[[package]]
+name = "hashbrown"
+version = "0.13.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43a3c133739dddd0d2990f9a4bdf8eb4b21ef50e4851ca85ab661199821d510e"
 dependencies = [
  "ahash",
 ]
@@ -1010,15 +1051,6 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
 
-[[package]]
-name = "hermit-abi"
-version = "0.2.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ee512640fe35acbfb4bb779db6f0d80704c2cacfa2e39b601ef3e3f47d1ae4c7"
-dependencies = [
- "libc",
-]
-
 [[package]]
 name = "hermit-abi"
 version = "0.3.1"
@@ -1087,9 +1119,9 @@ checksum = "c4a1e36c821dbe04574f602848a19f742f4fb3c98d40449f11bcad18d6b17421"
 
 [[package]]
 name = "hyper"
-version = "0.14.26"
+version = "0.14.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ab302d72a6f11a3b910431ff93aae7e773078c769f0a3ef15fb9ec692ed147d4"
+checksum = "ffb1cfd654a8219eaef89881fdb3bb3b1cdc5fa75ded05d6933b2b382e395468"
 dependencies = [
  "bytes",
  "futures-channel",
@@ -1157,7 +1189,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
 dependencies = [
  "autocfg",
- "hashbrown",
+ "hashbrown 0.12.3",
  "serde",
 ]
 
@@ -1209,26 +1241,25 @@ version = "1.0.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "eae7b9aee968036d54dce06cebaefd919e4472e753296daccd6d344e3e2df0c2"
 dependencies = [
- "hermit-abi 0.3.1",
+ "hermit-abi",
  "libc",
  "windows-sys 0.48.0",
 ]
 
 [[package]]
 name = "ipnet"
-version = "2.7.2"
+version = "2.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "12b6ee2129af8d4fb011108c73d99a1b83a85977f23b82460c0ae2e25bb4b57f"
+checksum = "28b29a3cd74f0f4598934efe3aeba42bae0eb4680554128851ebbecb02af14e6"
 
 [[package]]
 name = "is-terminal"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "adcf93614601c8129ddf72e2d5633df827ba6551541c6d8c59520a371475be1f"
+checksum = "24fddda5af7e54bf7da53067d6e802dbcc381d0a8eef629df528e3ebf68755cb"
 dependencies = [
- "hermit-abi 0.3.1",
- "io-lifetimes",
- "rustix",
+ "hermit-abi",
+ "rustix 0.38.1",
  "windows-sys 0.48.0",
 ]
 
@@ -1291,9 +1322,9 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
-version = "0.2.146"
+version = "0.2.147"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f92be4933c13fd498862a9e02a3055f8a8d9c039ce33db97306fd5a6caa7f29b"
+checksum = "b4668fb0ea861c1df094127ac5f1da3409a82116a4ba74fca2e58ef927159bb3"
 
 [[package]]
 name = "libm"
@@ -1307,6 +1338,12 @@ version = "0.3.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ef53942eb7bf7ff43a617b3e2c1c4a5ecf5944a7c1bc12d7ee39bbb15e5c1519"
 
+[[package]]
+name = "linux-raw-sys"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09fc20d2ca12cb9f044c93e3bd6d32d523e6e2ec3db4f7b2939cd99026ecd3f0"
+
 [[package]]
 name = "lock_api"
 version = "0.4.10"
@@ -1324,10 +1361,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b06a4cde4c0f271a446782e3eff8de789548ce57dbc8eca9292c27f4a42004b4"
 
 [[package]]
-name = "mach"
-version = "0.3.2"
+name = "mach2"
+version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b823e83b2affd8f40a9ee8c29dbc56404c1e34cd2710921f2801e2cf29527afa"
+checksum = "6d0d1830bcd151a6fc4aea1369af235b36c1528fe976b8ff678683c9995eade8"
 dependencies = [
  "libc",
 ]
@@ -1386,28 +1423,27 @@ dependencies = [
 
 [[package]]
 name = "metrics"
-version = "0.20.1"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b9b8653cec6897f73b519a43fba5ee3d50f62fe9af80b428accdcc093b4a849"
+checksum = "aa8ebbd1a9e57bbab77b9facae7f5136aea44c356943bf9a198f647da64285d6"
 dependencies = [
  "ahash",
  "metrics-macros",
- "portable-atomic 0.3.20",
+ "portable-atomic",
 ]
 
 [[package]]
 name = "metrics-exporter-prometheus"
-version = "0.11.0"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8603921e1f54ef386189335f288441af761e0fc61bcb552168d9cedfe63ebc70"
+checksum = "8a4964177ddfdab1e3a2b37aec7cf320e14169abb0ed73999f558136409178d5"
 dependencies = [
+ "base64 0.21.2",
  "hyper",
  "indexmap",
  "ipnet",
  "metrics",
  "metrics-util",
- "parking_lot",
- "portable-atomic 0.3.20",
  "quanta",
  "thiserror",
  "tokio",
@@ -1416,28 +1452,26 @@ dependencies = [
 
 [[package]]
 name = "metrics-macros"
-version = "0.6.0"
+version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "731f8ecebd9f3a4aa847dfe75455e4757a45da40a7793d2f0b1f9b6ed18b23f3"
+checksum = "ddece26afd34c31585c74a4db0630c376df271c285d682d1e55012197830b6df"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 1.0.109",
+ "syn 2.0.22",
 ]
 
 [[package]]
 name = "metrics-util"
-version = "0.14.0"
+version = "0.15.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7d24dc2dbae22bff6f1f9326ffce828c9f07ef9cc1e8002e5279f845432a30a"
+checksum = "111cb375987443c3de8d503580b536f77dc8416d32db62d9456db5d93bd7ac47"
 dependencies = [
  "crossbeam-epoch",
  "crossbeam-utils",
- "hashbrown",
+ "hashbrown 0.13.2",
  "metrics",
  "num_cpus",
- "parking_lot",
- "portable-atomic 0.3.20",
  "quanta",
  "sketches-ddsketch",
 ]
@@ -1481,7 +1515,7 @@ checksum = "927a765cd3fc26206e66b296465fa9d3e5ab003e651c1b3c060e7956d96b19d2"
 dependencies = [
  "libc",
  "log",
- "wasi 0.11.0+wasi-snapshot-preview1",
+ "wasi",
  "windows-sys 0.48.0",
 ]
 
@@ -1503,7 +1537,7 @@ checksum = "8795add3e14028f11f8e848bd3294898a8294767b3776b6f733560d33bd2530b"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -1520,7 +1554,7 @@ checksum = "e92b89ac3127251efde6f5a9586e5aae99468d06fcf9f133b377f58d5ed66446"
 dependencies = [
  "async-trait",
  "awaitdrop",
- "bitflags",
+ "bitflags 1.3.2",
  "bytes",
  "futures",
  "pin-project",
@@ -1560,9 +1594,9 @@ dependencies = [
 
 [[package]]
 name = "ngrok"
-version = "0.12.3"
+version = "0.12.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "98ce3514eec7338e2d4663e3efb4429e08d8f3662996be4b9585350e7d8ad728"
+checksum = "87e211f407b0a084f720823a00c956aeab2c15dfe7a61760d93227bbaf048026"
 dependencies = [
  "arc-swap",
  "async-rustls",
@@ -1595,7 +1629,7 @@ version = "0.26.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bfdda3d196821d6af13126e40375cdf7da646a96114af134d5f417a9a1dc8e1a"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "cfg-if",
  "libc",
  "static_assertions",
@@ -1648,11 +1682,11 @@ dependencies = [
 
 [[package]]
 name = "num_cpus"
-version = "1.15.0"
+version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fac9e2da13b5eb447a6ce3d392f23a29d8694bff781bf03a16cd9ac8697593b"
+checksum = "4161fcb6d602d4d2081af7c3a45852d875a03dd337a6bfdd6e06407b61342a43"
 dependencies = [
- "hermit-abi 0.2.6",
+ "hermit-abi",
  "libc",
 ]
 
@@ -1668,6 +1702,15 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
+[[package]]
+name = "object"
+version = "0.31.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8bda667d9f2b5051b8833f59f3bf748b28ef54f850f4fcb389a252aa383866d1"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.18.0"
@@ -1680,7 +1723,7 @@ version = "6.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8c4b31c8722ad9171c6d77d3557db078cab2bd50afcc9d09c8b315c59df8ca4f"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "libc",
  "once_cell",
  "onig_sys",
@@ -1698,11 +1741,11 @@ dependencies = [
 
 [[package]]
 name = "openssl"
-version = "0.10.54"
+version = "0.10.55"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "69b3f656a17a6cbc115b5c7a40c616947d213ba182135b014d6051b73ab6f019"
+checksum = "345df152bc43501c5eb9e4654ff05f794effb78d4efe3d53abc158baddc0703d"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "cfg-if",
  "foreign-types",
  "libc",
@@ -1719,7 +1762,7 @@ checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -1730,9 +1773,9 @@ checksum = "ff011a302c396a5197692431fc1948019154afc178baf7d8e37367442a4601cf"
 
 [[package]]
 name = "openssl-sys"
-version = "0.9.88"
+version = "0.9.90"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c2ce0f250f34a308dcfdbb351f511359857d4ed2134ba715a4eadd46e1ffd617"
+checksum = "374533b0e45f3a7ced10fcaeccca020e66656bc03dac384f852e4e5a7a8104a6"
 dependencies = [
  "cc",
  "libc",
@@ -1746,40 +1789,49 @@ version = "0.18.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "69d6c3d7288a106c0a363e4b0e8d308058d56902adefb16f4936f417ffef086e"
 dependencies = [
- "opentelemetry_api",
- "opentelemetry_sdk",
+ "opentelemetry_api 0.18.0",
+ "opentelemetry_sdk 0.18.0",
+]
+
+[[package]]
+name = "opentelemetry"
+version = "0.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5f4b8347cc26099d3aeee044065ecc3ae11469796b4d65d065a23a584ed92a6f"
+dependencies = [
+ "opentelemetry_api 0.19.0",
+ "opentelemetry_sdk 0.19.0",
 ]
 
 [[package]]
 name = "opentelemetry-otlp"
-version = "0.11.0"
+version = "0.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1c928609d087790fc936a1067bdc310ae702bdf3b090c3f281b713622c8bbde"
+checksum = "8af72d59a4484654ea8eb183fea5ae4eb6a41d7ac3e3bae5f4d2a282a3a7d3ca"
 dependencies = [
  "async-trait",
  "futures",
  "futures-util",
  "http",
- "opentelemetry",
+ "opentelemetry 0.19.0",
  "opentelemetry-proto",
  "prost",
  "thiserror",
  "tokio",
- "tonic",
+ "tonic 0.8.3",
 ]
 
 [[package]]
 name = "opentelemetry-proto"
-version = "0.1.0"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d61a2f56df5574508dd86aaca016c917489e589ece4141df1b5e349af8d66c28"
+checksum = "045f8eea8c0fa19f7d48e7bc3128a39c2e5c533d5c61298c548dfefc1064474c"
 dependencies = [
  "futures",
  "futures-util",
- "opentelemetry",
+ "opentelemetry 0.19.0",
  "prost",
- "tonic",
- "tonic-build",
+ "tonic 0.8.3",
 ]
 
 [[package]]
@@ -1798,6 +1850,22 @@ dependencies = [
  "thiserror",
 ]
 
+[[package]]
+name = "opentelemetry_api"
+version = "0.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed41783a5bf567688eb38372f2b7a8530f5a607a4b49d38dd7573236c23ca7e2"
+dependencies = [
+ "fnv",
+ "futures-channel",
+ "futures-util",
+ "indexmap",
+ "once_cell",
+ "pin-project-lite",
+ "thiserror",
+ "urlencoding",
+]
+
 [[package]]
 name = "opentelemetry_sdk"
 version = "0.18.0"
@@ -1812,7 +1880,29 @@ dependencies = [
  "futures-executor",
  "futures-util",
  "once_cell",
- "opentelemetry_api",
+ "opentelemetry_api 0.18.0",
+ "percent-encoding",
+ "rand",
+ "thiserror",
+ "tokio",
+ "tokio-stream",
+]
+
+[[package]]
+name = "opentelemetry_sdk"
+version = "0.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b3a2a91fdbfdd4d212c0dcc2ab540de2c2bcbbd90be17de7a7daf8822d010c1"
+dependencies = [
+ "async-trait",
+ "crossbeam-channel",
+ "dashmap",
+ "fnv",
+ "futures-channel",
+ "futures-executor",
+ "futures-util",
+ "once_cell",
+ "opentelemetry_api 0.19.0",
  "percent-encoding",
  "rand",
  "thiserror",
@@ -1857,7 +1947,7 @@ dependencies = [
  "libc",
  "redox_syscall 0.3.5",
  "smallvec",
- "windows-targets 0.48.0",
+ "windows-targets 0.48.1",
 ]
 
 [[package]]
@@ -1907,22 +1997,22 @@ dependencies = [
 
 [[package]]
 name = "pin-project"
-version = "1.1.0"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c95a7476719eab1e366eaf73d0260af3021184f18177925b07f54b30089ceead"
+checksum = "6e138fdd8263907a2b0e1b4e80b7e58c721126479b6e6eedfb1b402acea7b9bd"
 dependencies = [
  "pin-project-internal",
 ]
 
 [[package]]
 name = "pin-project-internal"
-version = "1.1.0"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "39407670928234ebc5e6e580247dd567ad73a3578460c5990f9503df207e8f07"
+checksum = "d1fef411b303e3e12d534fb6e7852de82da56edd937d895125821fb7c09436c7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -1943,15 +2033,6 @@ version = "0.3.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "26072860ba924cbfa98ea39c8c19b4dd6a4a25423dbdf219c1eca91aa0cf6964"
 
-[[package]]
-name = "portable-atomic"
-version = "0.3.20"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e30165d31df606f5726b090ec7592c308a0eaf61721ff64c9a3018e344a8753e"
-dependencies = [
- "portable-atomic 1.3.3",
-]
-
 [[package]]
 name = "portable-atomic"
 version = "1.3.3"
@@ -2000,9 +2081,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.60"
+version = "1.0.63"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dec2b086b7a862cf4de201096214fa870344cf922b2b30c167badb3af3195406"
+checksum = "7b368fba921b0dce7e60f5e04ec15e565b3303972b42bcfde1d0713b881959eb"
 dependencies = [
  "unicode-ident",
 ]
@@ -2063,25 +2144,25 @@ dependencies = [
 
 [[package]]
 name = "quanta"
-version = "0.10.1"
+version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b7e31331286705f455e56cca62e0e717158474ff02b7936c1fa596d983f4ae27"
+checksum = "a17e662a7a8291a865152364c20c7abc5e60486ab2001e8ec10b24862de0b9ab"
 dependencies = [
  "crossbeam-utils",
  "libc",
- "mach",
+ "mach2",
  "once_cell",
  "raw-cpuid",
- "wasi 0.10.2+wasi-snapshot-preview1",
+ "wasi",
  "web-sys",
  "winapi",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.28"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b9ab9c7eadfd8df19006f1cf1a4aed13540ed5cbc047010ece5826e10825488"
+checksum = "573015e8ab27661678357f27dc26460738fd2b6c86e46f386fde94cb5d913105"
 dependencies = [
  "proc-macro2",
 ]
@@ -2122,7 +2203,7 @@ version = "0.20.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dcc0d032bccba900ee32151ec0265667535c230169f5a011154cdcd984e16829"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "cassowary",
  "crossterm",
  "unicode-segmentation",
@@ -2135,7 +2216,7 @@ version = "10.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6c297679cb867470fa8c9f67dbba74a78d78e3e98d7cf2b08d6d71540f797332"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
 ]
 
 [[package]]
@@ -2177,7 +2258,7 @@ version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
 ]
 
 [[package]]
@@ -2186,7 +2267,7 @@ version = "0.3.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "567664f262709473930a4bf9e51bf2ebf3348f2e748ccc50dea20646858f8f29"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
 ]
 
 [[package]]
@@ -2286,9 +2367,9 @@ dependencies = [
 
 [[package]]
 name = "rust-embed"
-version = "6.7.0"
+version = "6.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b73e721f488c353141288f223b599b4ae9303ecf3e62923f40a492f0634a4dc3"
+checksum = "a36224c3276f8c4ebc8c20f158eca7ca4359c8db89991c4925132aaaf6702661"
 dependencies = [
  "rust-embed-impl",
  "rust-embed-utils",
@@ -2297,28 +2378,34 @@ dependencies = [
 
 [[package]]
 name = "rust-embed-impl"
-version = "6.6.0"
+version = "6.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e22ce362f5561923889196595504317a4372b84210e6e335da529a65ea5452b5"
+checksum = "49b94b81e5b2c284684141a2fb9e2a31be90638caf040bf9afbc5a0416afe1ac"
 dependencies = [
  "proc-macro2",
  "quote",
  "rust-embed-utils",
  "shellexpand",
- "syn 2.0.18",
+ "syn 2.0.22",
  "walkdir",
 ]
 
 [[package]]
 name = "rust-embed-utils"
-version = "7.5.0"
+version = "7.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "512b0ab6853f7e14e3c8754acb43d6f748bb9ced66aa5915a6553ac8213f7731"
+checksum = "9d38ff6bf570dc3bb7100fce9f7b60c33fa71d80e88da3f2580df4ff2bdded74"
 dependencies = [
  "sha2",
  "walkdir",
 ]
 
+[[package]]
+name = "rustc-demangle"
+version = "0.1.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d626bb9dae77e28219937af045c257c28bfd3f69333c512553507f5f9798cb76"
+
 [[package]]
 name = "rustc_version"
 version = "0.4.0"
@@ -2330,15 +2417,28 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.37.20"
+version = "0.37.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b96e891d04aa506a6d1f318d2771bcb1c7dfda84e126660ace067c9b474bb2c0"
+checksum = "62f25693a73057a1b4cb56179dd3c7ea21a7c6c5ee7d85781f5749b46f34b79c"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "errno",
  "io-lifetimes",
  "libc",
- "linux-raw-sys",
+ "linux-raw-sys 0.3.8",
+ "windows-sys 0.48.0",
+]
+
+[[package]]
+name = "rustix"
+version = "0.38.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fbc6396159432b5c8490d4e301d8c705f61860b8b6c863bf79942ce5401968f3"
+dependencies = [
+ "bitflags 2.3.3",
+ "errno",
+ "libc",
+ "linux-raw-sys 0.4.3",
  "windows-sys 0.48.0",
 ]
 
@@ -2356,9 +2456,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-pemfile"
-version = "1.0.2"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d194b56d58803a43635bdc398cd17e383d6f71f9182b9a192c127ca42494a59b"
+checksum = "2d3987094b1d07b653b7dfdc3f70ce9a1da9c51ac18c1b06b662e4f9a0e9f4b2"
 dependencies = [
  "base64 0.21.2",
 ]
@@ -2415,7 +2515,7 @@ version = "2.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1fc758eb7bffce5b308734e9b0c1468893cae9ff70ebf13e7090be8dcbcc83a8"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "core-foundation",
  "core-foundation-sys",
  "libc",
@@ -2455,14 +2555,14 @@ checksum = "d9735b638ccc51c28bf6914d90a2e9725b377144fc612c49a611fddd1b631d68"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.97"
+version = "1.0.99"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bdf3bf93142acad5821c99197022e170842cdbc1c30482b98750c688c640842a"
+checksum = "46266871c240a00b8f503b877622fe33430b3c7d963bdc0f2adc511e54a1eae3"
 dependencies = [
  "itoa",
  "ryu",
@@ -2668,9 +2768,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.18"
+version = "2.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32d41677bcbe24c20c52e7c70b0d8db04134c5d1066bf98662e2871ad200ea3e"
+checksum = "2efbeae7acf4eabd6bcdcbd11c92f45231ddda7539edc7806bd1a04a03b24616"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -2685,9 +2785,9 @@ checksum = "2047c6ded9c721764247e62cd3b03c09ffc529b2ba5b10ec482ae507a4a70160"
 
 [[package]]
 name = "sysinfo"
-version = "0.29.2"
+version = "0.29.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9557d0845b86eea8182f7b10dff120214fb6cd9fd937b6f4917714e546a38695"
+checksum = "5bcd0346f90b6bc83526c7b180039a8acd26a5c848cc556d457f6472eb148122"
 dependencies = [
  "cfg-if",
  "core-foundation-sys",
@@ -2742,13 +2842,13 @@ dependencies = [
  "cfg-if",
  "fastrand",
  "redox_syscall 0.3.5",
- "rustix",
+ "rustix 0.37.21",
  "windows-sys 0.48.0",
 ]
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.8.2"
+version = "0.9.0"
 dependencies = [
  "average",
  "clap",
@@ -2768,7 +2868,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.8.2"
+version = "0.9.0"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2776,7 +2876,7 @@ dependencies = [
  "prost-build",
  "thiserror",
  "tokio",
- "tonic",
+ "tonic 0.9.2",
  "tonic-build",
  "tower",
  "tracing",
@@ -2784,7 +2884,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.8.2"
+version = "0.9.0"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2800,7 +2900,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.8.2"
+version = "0.9.0"
 dependencies = [
  "async-stream",
  "axum",
@@ -2812,7 +2912,7 @@ dependencies = [
  "metrics-exporter-prometheus",
  "ngrok",
  "nohash-hasher",
- "opentelemetry",
+ "opentelemetry 0.19.0",
  "opentelemetry-otlp",
  "rand",
  "reqwest",
@@ -2822,9 +2922,9 @@ dependencies = [
  "thiserror",
  "tokenizers",
  "tokio",
- "tower-http 0.4.0",
+ "tower-http 0.4.1",
  "tracing",
- "tracing-opentelemetry",
+ "tracing-opentelemetry 0.19.0",
  "tracing-subscriber",
  "utoipa",
  "utoipa-swagger-ui",
@@ -2848,7 +2948,7 @@ checksum = "f9456a42c5b0d803c8cd86e73dd7cc9edd429499f37a3550d286d5e86720569f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -2941,11 +3041,12 @@ dependencies = [
 
 [[package]]
 name = "tokio"
-version = "1.28.2"
+version = "1.29.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "94d7b1cfd2aa4011f2de74c2c4c63665e27a71006b0a192dcd2710272e73dfa2"
+checksum = "532826ff75199d5833b9d2c5fe410f29235e25704ee5f0ef599fb51c21f4a4da"
 dependencies = [
  "autocfg",
+ "backtrace",
  "bytes",
  "libc",
  "mio",
@@ -2976,7 +3077,7 @@ checksum = "630bdcf245f78637c13ec01ffae6187cca34625e8c63150d424b59e55af2675e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -3059,10 +3160,38 @@ dependencies = [
 ]
 
 [[package]]
-name = "tonic-build"
-version = "0.8.4"
+name = "tonic"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5bf5e9b9c0f7e0a7c027dcfaba7b2c60816c7049171f679d99ee2ff65d0de8c4"
+checksum = "3082666a3a6433f7f511c7192923fa1fe07c69332d3c6a2e6bb040b569199d5a"
+dependencies = [
+ "async-trait",
+ "axum",
+ "base64 0.21.2",
+ "bytes",
+ "futures-core",
+ "futures-util",
+ "h2",
+ "http",
+ "http-body",
+ "hyper",
+ "hyper-timeout",
+ "percent-encoding",
+ "pin-project",
+ "prost",
+ "tokio",
+ "tokio-stream",
+ "tower",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "tonic-build"
+version = "0.9.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a6fdaae4c2c638bb70fe42803a26fbd6fc6ac8c72f5c59f67ecc2a2dcabf4b07"
 dependencies = [
  "prettyplease",
  "proc-macro2",
@@ -3097,7 +3226,7 @@ version = "0.3.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f873044bf02dd1e8239e9c1293ea39dad76dc594ec16185d0a1bf31d8dc8d858"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
  "bytes",
  "futures-core",
  "futures-util",
@@ -3112,11 +3241,11 @@ dependencies = [
 
 [[package]]
 name = "tower-http"
-version = "0.4.0"
+version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5d1d42a9b3f3ec46ba828e8d376aec14592ea199f70a06a548587ecd1c4ab658"
+checksum = "a8bd22a874a2d0b70452d5597b12c537331d49060824a95f49f108994f94aa4c"
 dependencies = [
- "bitflags",
+ "bitflags 2.3.3",
  "bytes",
  "futures-core",
  "futures-util",
@@ -3155,13 +3284,13 @@ dependencies = [
 
 [[package]]
 name = "tracing-attributes"
-version = "0.1.24"
+version = "0.1.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0f57e3ca2a01450b1a921183a9c9cbfda207fd822cef4ccb00a65402cbba7a74"
+checksum = "5f4f31f56159e98206da9efd823404b79b6ef3143b4a7ab76e67b1751b25a4ab"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -3202,7 +3331,21 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "21ebb87a95ea13271332df069020513ab70bdb5637ca42d6e492dc3bbbad48de"
 dependencies = [
  "once_cell",
- "opentelemetry",
+ "opentelemetry 0.18.0",
+ "tracing",
+ "tracing-core",
+ "tracing-log",
+ "tracing-subscriber",
+]
+
+[[package]]
+name = "tracing-opentelemetry"
+version = "0.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "00a39dcf9bfc1742fa4d6215253b33a6e474be78275884c216fc2a06267b3600"
+dependencies = [
+ "once_cell",
+ "opentelemetry 0.19.0",
  "tracing",
  "tracing-core",
  "tracing-log",
@@ -3326,6 +3469,12 @@ dependencies = [
  "percent-encoding",
 ]
 
+[[package]]
+name = "urlencoding"
+version = "2.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8db7427f936968176eaa7cdf81b7f98b980b18495ec28f1b5791ac3bfe3eea9"
+
 [[package]]
 name = "utf8parse"
 version = "0.2.1"
@@ -3353,7 +3502,7 @@ dependencies = [
  "proc-macro-error",
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
 ]
 
 [[package]]
@@ -3422,12 +3571,6 @@ dependencies = [
  "try-lock",
 ]
 
-[[package]]
-name = "wasi"
-version = "0.10.2+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6"
-
 [[package]]
 name = "wasi"
 version = "0.11.0+wasi-snapshot-preview1"
@@ -3455,7 +3598,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
  "wasm-bindgen-shared",
 ]
 
@@ -3489,7 +3632,7 @@ checksum = "54681b18a46765f095758388f2d0cf16eb8d4169b639ab575a8f5693af210c7b"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.18",
+ "syn 2.0.22",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
@@ -3592,7 +3735,7 @@ version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
 dependencies = [
- "windows-targets 0.48.0",
+ "windows-targets 0.48.1",
 ]
 
 [[package]]
@@ -3612,9 +3755,9 @@ dependencies = [
 
 [[package]]
 name = "windows-targets"
-version = "0.48.0"
+version = "0.48.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b1eb6f0cd7c80c79759c929114ef071b87354ce476d9d94271031c0497adfd5"
+checksum = "05d4b17490f70499f20b9e791dcf6a299785ce8af4d709018206dc5b4953e95f"
 dependencies = [
  "windows_aarch64_gnullvm 0.48.0",
  "windows_aarch64_msvc 0.48.0",
diff --git a/Cargo.toml b/Cargo.toml
index b28286fa..ba7a920d 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.8.2"
+version = "0.9.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/Dockerfile b/Dockerfile
index 1a969383..66e0091d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,5 +1,5 @@
 # Rust builder
-FROM lukemathwalker/cargo-chef:latest-rust-1.69 AS chef
+FROM lukemathwalker/cargo-chef:latest-rust-1.70 AS chef
 WORKDIR /usr/src
 
 ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
diff --git a/README.md b/README.md
index b74d2617..d31c176b 100644
--- a/README.md
+++ b/README.md
@@ -84,7 +84,7 @@ model=bigscience/bloom-560m
 num_shard=2
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.8 --model-id $model --num-shard $num_shard
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.9 --model-id $model --num-shard $num_shard
 ```
 **Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.
 
diff --git a/aml/README.md b/aml/README.md
deleted file mode 100644
index 8e78b0ab..00000000
--- a/aml/README.md
+++ /dev/null
@@ -1,15 +0,0 @@
-# Azure ML endpoint
-
-## Create all resources
-
-```shell
-az ml model create -f model.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace
-az ml online-endpoint create -f endpoint.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace
-az ml online-deployment create -f deployment.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace
-```
-
-## Update deployment
-
-```shell
-az ml online-deployment update -f deployment.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace
-```
\ No newline at end of file
diff --git a/aml/deployment.yaml b/aml/deployment.yaml
deleted file mode 100644
index 320eba24..00000000
--- a/aml/deployment.yaml
+++ /dev/null
@@ -1,38 +0,0 @@
-$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json
-name: bloom-deployment
-endpoint_name: bloom-inference
-model: azureml:bloom-safetensors:1
-model_mount_path: /var/azureml-model
-environment_variables:
-  WEIGHTS_CACHE_OVERRIDE: /var/azureml-model/bloom-safetensors
-  MODEL_ID: bigscience/bloom
-  NUM_SHARD: 8
-environment:
-  image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:0.2.0
-  inference_config:
-    liveness_route:
-      port: 80
-      path: /health
-    readiness_route:
-      port: 80
-      path: /health
-    scoring_route:
-      port: 80
-      path: /generate
-instance_type: Standard_ND96amsr_A100_v4
-request_settings:
-  request_timeout_ms: 90000
-  max_concurrent_requests_per_instance: 256
-liveness_probe:
-  initial_delay: 600
-  timeout: 90
-  period: 120
-  success_threshold: 1
-  failure_threshold: 5
-readiness_probe:
-  initial_delay: 600
-  timeout: 90
-  period: 120
-  success_threshold: 1
-  failure_threshold: 5
-instance_count: 1
diff --git a/aml/endpoint.yaml b/aml/endpoint.yaml
deleted file mode 100644
index f2f01d5e..00000000
--- a/aml/endpoint.yaml
+++ /dev/null
@@ -1,3 +0,0 @@
-$schema: https://azuremlsdk2.blob.core.windows.net/latest/managedOnlineEndpoint.schema.json
-name: bloom-inference
-auth_mode: key
diff --git a/aml/model.yaml b/aml/model.yaml
deleted file mode 100644
index bfcdd33f..00000000
--- a/aml/model.yaml
+++ /dev/null
@@ -1,3 +0,0 @@
-$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
-name: bloom-safetensors
-path: /data/bloom-safetensors
diff --git a/docs/openapi.json b/docs/openapi.json
index 8c652946..b91729d0 100644
--- a/docs/openapi.json
+++ b/docs/openapi.json
@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "0.8.2"
+    "version": "0.9.0"
   },
   "paths": {
     "/": {
@@ -270,6 +270,35 @@
         }
       }
     },
+    "/health": {
+      "get": {
+        "tags": [
+          "Text Generation Inference"
+        ],
+        "summary": "Health check method",
+        "description": "Health check method",
+        "operationId": "health",
+        "responses": {
+          "200": {
+            "description": "Everything is working fine"
+          },
+          "503": {
+            "description": "Text generation inference is down",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                },
+                "example": {
+                  "error": "unhealthy",
+                  "error_type": "healthcheck"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/info": {
       "get": {
         "tags": [
diff --git a/launcher/src/main.rs b/launcher/src/main.rs
index 30abe88a..5b5cb45e 100644
--- a/launcher/src/main.rs
+++ b/launcher/src/main.rs
@@ -1040,14 +1040,18 @@ fn main() -> Result<(), LauncherError> {
         return Ok(());
     }
 
-    let mut webserver = spawn_webserver(args, shutdown.clone(), &shutdown_receiver)?;
+    let mut webserver =
+        spawn_webserver(args, shutdown.clone(), &shutdown_receiver).map_err(|err| {
+            shutdown_shards(shutdown.clone(), &shutdown_receiver);
+            err
+        })?;
 
     // Default exit code
     let mut exit_code = Ok(());
 
     while running.load(Ordering::SeqCst) {
         if let Ok(ShardStatus::Failed((rank, err))) = status_receiver.try_recv() {
-            tracing::error!("Shard {rank} failed to start");
+            tracing::error!("Shard {rank} crashed");
             if let Some(err) = err {
                 tracing::error!("{err}");
             }
diff --git a/router/Cargo.toml b/router/Cargo.toml
index c1e665b1..10396826 100644
--- a/router/Cargo.toml
+++ b/router/Cargo.toml
@@ -22,11 +22,11 @@ text-generation-client = { path = "client" }
 clap = { version = "4.1.4", features = ["derive", "env"] }
 flume = "0.10.14"
 futures = "0.3.26"
-metrics = "0.20.1"
-metrics-exporter-prometheus = { version = "0.11.0", features = [] }
+metrics = "0.21.0"
+metrics-exporter-prometheus = { version = "0.12.1", features = [] }
 nohash-hasher = "0.2.0"
-opentelemetry = { version = "0.18.0", features = ["rt-tokio"] }
-opentelemetry-otlp = "0.11.0"
+opentelemetry = { version = "0.19.0", features = ["rt-tokio"] }
+opentelemetry-otlp = "0.12.0"
 rand = "0.8.5"
 reqwest = { version = "0.11.14", features = [] }
 serde = "1.0.152"
@@ -36,7 +36,7 @@ tokenizers = "0.13.3"
 tokio = { version = "1.25.0", features = ["rt", "rt-multi-thread", "parking_lot", "signal", "sync"] }
 tower-http = { version = "0.4.0", features = ["cors"] }
 tracing = "0.1.37"
-tracing-opentelemetry = "0.18.0"
+tracing-opentelemetry = "0.19.0"
 tracing-subscriber = { version = "0.3.16", features = ["json", "env-filter"] }
 utoipa = { version = "3.0.1", features = ["axum_extras"] }
 utoipa-swagger-ui = { version = "3.0.2", features = ["axum"] }
diff --git a/router/client/Cargo.toml b/router/client/Cargo.toml
index db7245e0..43f444e6 100644
--- a/router/client/Cargo.toml
+++ b/router/client/Cargo.toml
@@ -11,10 +11,10 @@ grpc-metadata = { path = "../grpc-metadata" }
 prost = "^0.11"
 thiserror = "^1.0"
 tokio = { version = "^1.25", features = ["sync"] }
-tonic = "^0.8"
+tonic = "^0.9"
 tower = "^0.4"
 tracing = "^0.1"
 
 [build-dependencies]
-tonic-build = "0.8.4"
+tonic-build = "0.9.2"
 prost-build = "0.11.6"
diff --git a/router/grpc-metadata/Cargo.toml b/router/grpc-metadata/Cargo.toml
index 311092e3..9e01f527 100644
--- a/router/grpc-metadata/Cargo.toml
+++ b/router/grpc-metadata/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
-opentelemetry = "0.18.0"
-tonic = "^0.8"
+opentelemetry = "^0.19"
+tonic = "^0.9"
 tracing = "^0.1"
-tracing-opentelemetry = "0.18.0"
+tracing-opentelemetry = "^0.19"
diff --git a/router/src/server.rs b/router/src/server.rs
index ee96ead6..54418f84 100644
--- a/router/src/server.rs
+++ b/router/src/server.rs
@@ -532,6 +532,7 @@ pub async fn run(
     #[derive(OpenApi)]
     #[openapi(
         paths(
+            health,
             get_model_info,
             compat_generate,
             generate,
diff --git a/rust-toolchain.toml b/rust-toolchain.toml
index d6ecf0c4..2db1883c 100644
--- a/rust-toolchain.toml
+++ b/rust-toolchain.toml
@@ -1,3 +1,3 @@
 [toolchain]
-channel = "1.69.0"
+channel = "1.70.0"
 components = ["rustfmt", "clippy"]
\ No newline at end of file
diff --git a/server/pyproject.toml b/server/pyproject.toml
index f0ec25eb..294bcfc0 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.8.2"
+version = "0.9.0"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]