From 1be9c1ef4ac79264158d7dddf8261ecf5b866044 Mon Sep 17 00:00:00 2001 From: Cromefire_ Date: Sun, 10 Dec 2023 15:27:23 +0100 Subject: [PATCH] Pulled build improvements from #902 --- crates/llama-cpp-bindings/build.rs | 10 ++++++---- crates/llama-cpp-bindings/src/llama.rs | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/crates/llama-cpp-bindings/build.rs b/crates/llama-cpp-bindings/build.rs index b4e09f6c850..48520af374e 100644 --- a/crates/llama-cpp-bindings/build.rs +++ b/crates/llama-cpp-bindings/build.rs @@ -33,7 +33,7 @@ fn main() { println!("cargo:rustc-link-lib=cublasLt"); } if cfg!(feature = "rocm") { - let amd_gpu_targets: Vec<&str> = vec![ + let amd_gpu_default_targets: Vec<&str> = vec![ "gfx803", "gfx900", "gfx906:xnack-", @@ -51,6 +51,8 @@ fn main() { "gfx1102", "gfx1103", ]; + let amd_gpu_targets = + env::var("AMDGPU_TARGETS").unwrap_or(amd_gpu_default_targets.join(";")); let rocm_root = env::var("ROCM_ROOT").unwrap_or("/opt/rocm".to_string()); config.define("LLAMA_HIPBLAS", "ON"); @@ -59,7 +61,7 @@ fn main() { "CMAKE_CXX_COMPILER", format!("{}/llvm/bin/clang++", rocm_root), ); - config.define("AMDGPU_TARGETS", amd_gpu_targets.join(";")); + config.define("AMDGPU_TARGETS", amd_gpu_targets); println!("cargo:rustc-link-arg=-Wl,--copy-dt-needed-entries"); println!("cargo:rustc-link-search=native={}/hip/lib", rocm_root); println!("cargo:rustc-link-search=native={}/rocblas/lib", rocm_root); @@ -74,8 +76,8 @@ fn main() { cxx_build::bridge("src/lib.rs") .file("src/engine.cc") - .flag_if_supported("-Iinclude") - .flag_if_supported("-Illama.cpp") + .include("include") + .include("llama.cpp") .flag_if_supported("-std=c++14") .compile("cxxbridge"); } diff --git a/crates/llama-cpp-bindings/src/llama.rs b/crates/llama-cpp-bindings/src/llama.rs index 15db1358dc5..b288a3adc26 100644 --- a/crates/llama-cpp-bindings/src/llama.rs +++ b/crates/llama-cpp-bindings/src/llama.rs @@ -83,7 +83,7 @@ impl LlamaServiceImpl { }; for ffi::StepOutput { request_id, text } in result { - let mut stopped = false; + let mut stopped; let LlamaRunningRequest { tx, stop_condition } = self.requests.get_mut(&request_id).unwrap();