mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
* Add llamacpp backend Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Get rid of llama_batch_get_one() Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Use max_batch_total_tokens Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Handle max_batch_size Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add some input validation checks Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Handle ctx args & fix sampling Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add GPU args Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add --defrag-threshold Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add a stupid batch mechanism Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Cleanup Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add --numa Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix args Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Enable flash attention by default Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add --offload-kqv Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix batch_pos Signed-off-by: Adrien Gallouët <angt@huggingface.co> * backend(llama): add CUDA Dockerfile_llamacpp for now * Only export the latest logits Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Output real logprobs Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix batching Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix seq iterations Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Auto-detect n_threads when not provided Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Clear request cache after completion Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Remove warmup Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Cleanup Signed-off-by: Adrien Gallouët <angt@huggingface.co> * backend(llama): add CUDA architectures build argument for Dockerfile * Add specific args for batch Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add --type-v & --type-k Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Bump llamacpp to b4623 Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Disable graceful shutdown in debug mode Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update Dockerfile_llamacpp Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Cleanup Dockerfile Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update Cargo.lock Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update args Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Simplify batching logic Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Set TGI_LLAMA_PKG_CUDA from CUDA_VERSION Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Rename bindings Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Remove n_ctx Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Make max_batch_total_tokens optional Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Ensure all samplers are freed on error Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Initialize penalty_last_n with llamacpp default value Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Cleanup Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Improve default settings Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add doc Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update docs Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Thanks clippy Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Thanks cargo fmt Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update docs Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Do not use HOSTNAME env Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Bump llama.cpp & cuda Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix requirements.txt Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix fmt Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Enable KQV offload by default Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Remove Ngrok tunneling Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Remove .cargo/config.toml Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix Dockerfile Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add missing cuda prefix Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Handle custom llama.cpp dir Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Cleanup Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add README.md Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add HF transfer Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Fix bool args Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update doc Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Update doc Signed-off-by: Adrien Gallouët <angt@huggingface.co> --------- Signed-off-by: Adrien Gallouët <angt@huggingface.co> Co-authored-by: Morgan Funtowicz <funtowiczmo@gmail.com>
49 lines
1.6 KiB
Rust
49 lines
1.6 KiB
Rust
use bindgen::callbacks::{ItemInfo, ParseCallbacks};
|
|
use std::env;
|
|
use std::path::PathBuf;
|
|
|
|
#[derive(Debug)]
|
|
struct PrefixStripper;
|
|
|
|
impl ParseCallbacks for PrefixStripper {
|
|
fn generated_name_override(&self, item_info: ItemInfo<'_>) -> Option<String> {
|
|
item_info.name.strip_prefix("llama_").map(str::to_string)
|
|
}
|
|
}
|
|
|
|
fn main() {
|
|
if let Some(cuda_version) = option_env!("CUDA_VERSION") {
|
|
let mut version: Vec<&str> = cuda_version.split('.').collect();
|
|
if version.len() > 2 {
|
|
version.pop();
|
|
}
|
|
let cuda_version = format!("cuda-{}", version.join("."));
|
|
pkg_config::Config::new().probe(&cuda_version).unwrap();
|
|
}
|
|
let llama = pkg_config::Config::new().probe("llama").unwrap();
|
|
|
|
for path in &llama.link_paths {
|
|
println!("cargo:rustc-link-arg=-Wl,-rpath,{}", path.display());
|
|
}
|
|
println!("cargo:rustc-link-arg=-Wl,--disable-new-dtags");
|
|
|
|
let bindings = bindgen::Builder::default()
|
|
.clang_args(
|
|
llama
|
|
.include_paths
|
|
.iter()
|
|
.map(|p| format!("-I{}", p.display())),
|
|
)
|
|
.header_contents("llama_bindings.h", "#include <llama.h>")
|
|
.prepend_enum_name(false)
|
|
.parse_callbacks(Box::new(PrefixStripper))
|
|
.parse_callbacks(Box::new(bindgen::CargoCallbacks::new()))
|
|
.generate()
|
|
.expect("Unable to generate bindings");
|
|
|
|
let out_path = PathBuf::from(env::var("OUT_DIR").unwrap());
|
|
bindings
|
|
.write_to_file(out_path.join("llamacpp.rs"))
|
|
.expect("Couldn't write bindings!");
|
|
}
|