text-generation-inference/Cargo.toml
Funtowicz Morgan 17367438f3
Give TensorRT-LLMa proper CI/CD 😍 (#2886)
* test(ctest) enable address sanitizer

* feat(trtllm): expose finish reason to Rust

* feat(trtllm): fix logits retrieval

* misc(ci): enabe building tensorrt-llm

* misc(ci): update Rust action toolchain

* misc(ci): let's try to build the Dockerfile for trtllm

# Conflicts:
#	Dockerfile_trtllm

* misc(ci): provide mecanism to cache inside container

* misc(ci): export aws creds as output of step

* misc(ci): let's try this way

* misc(ci): again

* misc(ci): again

* misc(ci): add debug profile

* misc(ci): add debug profile

* misc(ci): lets actually use sccache ...

* misc(ci): do not build with ssl enabled

* misc(ci): WAT

* misc(ci): WAT

* misc(ci): WAT

* misc(ci): WAT

* misc(ci): WAT

* misc(backend): test with TGI S3 conf

* misc(backend): test with TGI S3 conf

* misc(backend): once more?

* misc(backend): let's try with GHA

* misc(backend): missing env directive

* misc(backend): make sure to correctly set IS_GHA_BUILD=true in wf

* misc(backend): ok let's debug smtg

* misc(backend): WWWWWWWWWWWWWAAAAAAAA

* misc(backend): kthxbye retry s3

* misc(backend): use session token

* misc(backend): add more info

* misc(backend): lets try 1h30

* misc(backend): lets try 1h30

* misc(backend): increase to 2h

* misc(backend): lets try...

* misc(backend): lets try...

* misc(backend): let's build for ci-runtime

* misc(backend): let's add some more tooling

* misc(backend): add some tags

* misc(backend): disable Werror for now

* misc(backend): added automatic gha detection

* misc(backend): remove leak sanitizer which is included in asan

* misc(backend): forward env

* misc(backend): forward env

* misc(backend): let's try

* misc(backend): let's try

* misc(backend): again

* misc(backend): again

* misc(backend): again

* misc(backend): again

* misc(backend): again

* misc(backend): fix sscache -> sccache

* misc(backend): fix sscache -> sccache

* misc(backend): fix sscache -> sccache

* misc(backend): let's actually cache things now

* misc(backend): let's actually cache things now

* misc(backend): attempt to run the testS?

* misc(backend): attempt to run the tests?

* misc(backend): attempt to run the tests?

* change runner size

* fix: Correctly tag docker images (#2878)

* fix: Correctly tag docker images

* fix: Correctly tag docker images

* misc(llamacpp): maybe?

* misc(llamacpp): maybe?

* misc(llamacpp): maybe?

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): go

* misc(ci): go

* misc(ci): go

* misc(ci): use bin folder

* misc(ci): make the wf callable for reuse

* misc(ci): make the wf callable for reuse (bis)

* misc(ci): make the wf callable for reuse (bis)

* misc(ci): give the wf a name

* Create test-trtllm.yml

* Update test-trtllm.yml

* Create build-trtllm2

* Rename build-trtllm2 to 1-build-trtllm2

* Rename test-trtllm.yml to 1-test-trtllm2.yml

* misc(ci): fw secrets

* Update 1-test-trtllm2.yml

* Rename 1-build-trtllm2 to 1-build-trtllm2.yml

* Update 1-test-trtllm2.yml

* misc(ci): use ci-build.yaml as main dispatcher

* Delete .github/workflows/1-test-trtllm2.yml

* Delete .github/workflows/1-build-trtllm2.yml

* misc(ci): rights?

* misc(ci): rights?

* misc(ci): once more?

* misc(ci): once more?

* misc(ci): baby more time?

* misc(ci): baby more time?

* misc(ci): try the permission above again?

* misc(ci): try the permission above again?

* misc(ci): try the permission scoped again?

* misc(ci): install tensorrt_llm_executor_static

* misc(ci): attempt to rebuild with sccache?

* misc(ci):run the tests on GPU instance

* misc(ci): let's actually setup sccache in the build.rs

* misc(ci): reintroduce variables

* misc(ci): enforce sccache

* misc(ci): correct right job name dependency

* misc(ci): detect dev profile for debug

* misc(ci): detect gha build

* misc(ci): detect gha build

* misc(ci): ok debug

* misc(ci): wtf

* misc(ci): wtf2

* misc(ci): wtf3

* misc(ci): use commit HEAD instead of merge commit for image id

* misc(ci): wtfinfini

* misc(ci): wtfinfini

* misc(ci): KAMEHAMEHA

* Merge TRTLLM in standard CI

* misc(ci): remove input machine

* misc(ci): missing id-token for AWS auth

* misc(ci): missing id-token for AWS auth

* misc(ci): missing id-token for AWS auth

* misc(ci): again...

* misc(ci): again...

* misc(ci): again...

* misc(ci): again...

* misc(ci): missing benchmark

* misc(ci): missing backends

* misc(ci): missing launcher

* misc(ci): give everything aws needs

* misc(ci): give everything aws needs

* misc(ci): fix warnings

* misc(ci): attempt to fix sccache not building trtllm

* misc(ci): attempt to fix sccache not building trtllm again

---------

Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>
Co-authored-by: Pauline Bailly-Masson <155966238+paulinebm@users.noreply.github.com>
2025-01-21 10:19:16 +01:00

54 lines
1.2 KiB
TOML

[workspace]
members = [
"benchmark",
"backends/v2",
"backends/v3",
"backends/grpc-metadata",
"backends/trtllm",
"launcher",
"router"
]
default-members = [
"benchmark",
"backends/v2",
"backends/v3",
"backends/grpc-metadata",
# "backends/trtllm",
"launcher",
"router"
]
resolver = "2"
[workspace.package]
version = "3.0.2-dev0"
edition = "2021"
authors = ["Olivier Dehaene"]
homepage = "https://github.com/huggingface/text-generation-inference"
[workspace.dependencies]
base64 = "0.22.0"
tokenizers = { version = "0.20.0", features = ["http"] }
hf-hub = { version = "0.3.1", features = ["tokio"] }
metrics = { version = "0.23.0" }
metrics-exporter-prometheus = { version = "0.15.1", features = [] }
minijinja = { version = "2.2.0", features = ["json"] }
minijinja-contrib = { version = "2.0.2", features = ["pycompat"] }
pyo3 = { version = "0.22.2", features = ["auto-initialize"] }
[profile.release]
incremental = true
[profile.release-binary]
inherits = "release"
debug = 1
incremental = true
panic = "abort"
[profile.release-opt]
inherits = "release"
debug = 0
incremental = false
lto = "fat"
opt-level = 3
codegen-units = 1