mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-25 03:12:13 +00:00
ea7f4082c4
* misc(cmake) update dependencies * feat(hardware) enable new hardware.hpp and unittests * test(ctest) enable address sanitizer * feat(backend): initial rewrite of the backend for simplicity * feat(backend): remove all the logs from hardware.hpp * feat(backend): added some logging * feat(backend): enable compiler warning if support for RVO not applying * feat(backend): missing return statement * feat(backend): introduce backend_workspace_t to store precomputed information from the engine folder * feat(backend): delete previous backend impl * feat(backend): more impl * feat(backend): use latest trtllm main version to have g++ >= 13 compatibility * feat(backend): allow overriding which Python to use * feat(backend): fix backend_exception_t -> backend_error_t naming * feat(backend): impl missing generation_step_t as return value of pull_tokens * feat(backend): make backend_workspace_t::engines_folder constexpr * feat(backend): fix main.rs retrieving the tokenizer * feat(backend): add guard to multiple header definitions * test(backend): add more unittest * feat(backend): remove constexpr from par * feat(backend): remove constexpig * test(backend): more test coverage * chore(trtllm): update dependency towards 0.15.0 * effectively cancel the request on the executor * feat(backend) fix moving backend when pulling * feat(backend): make sure we can easily cancel request on the executor * feat(backend): fix missing "0" field access * misc(backend): fix reborrowing Pin<&mut T> as described in the doc https://doc.rust-lang.org/stable/std/pin/struct.Pin.html#method.as_mut * chore: Add doc and CI for TRTLLM (#2799) * chore: Add doc and CI for TRTLLM * chore: Add doc and CI for TRTLLM * chore: Add doc and CI for TRTLLM * chore: Add doc and CI for TRTLLM * doc: Formatting * misc(backend): indent --------- Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>
30 lines
858 B
TOML
30 lines
858 B
TOML
[package]
|
|
name = "text-generation-backends-trtllm"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
authors.workspace = true
|
|
homepage.workspace = true
|
|
|
|
[dependencies]
|
|
async-trait = "0.1"
|
|
#async-stream = "0.3"
|
|
clap = { version = "4.5", features = ["derive"] }
|
|
cxx = "1.0"
|
|
hashbrown = "0.14"
|
|
hf-hub = { workspace = true }
|
|
#log = { version = "0.4", features = [] }
|
|
text-generation-router = { path = "../../router" }
|
|
tokenizers = { workspace = true }
|
|
tokio = { version = "1.39", features = ["rt", "rt-multi-thread", "parking_lot", "signal", "sync"] }
|
|
tokio-stream = "0.1.15"
|
|
thiserror = "1.0.63"
|
|
tracing = "0.1"
|
|
#tracing-opentelemetry = "0.25"
|
|
#tracing-subscriber = { version = "0.3", features = ["json", "env-filter"] }
|
|
pyo3 = { workspace = true }
|
|
|
|
[build-dependencies]
|
|
cmake = "0.1"
|
|
cxx-build = { version = "1.0", features = ["parallel"] }
|
|
pkg-config = "0.3"
|