text-generation-inference/launcher/src/env_runtime.rs
Wang, Yi d62c941c56
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
* clean cuda/rocm code in hpu backend, enable flat_hpu

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix TP in pageattn

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* adjust block table in hpu to improve performance

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* enable all the model. not testet yet

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* use tensor cache in hpu graph to avoid replay issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* add moe support, fix qwen/mistral/mixtral crash

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix phimoe issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* gpt_bigcode could also go pageattn

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* enable dbrx remove some unused code

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* multi-modality initial PR

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* adjust warmup and enable vlm

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix incorrect output in qwen2 idefics if hpu graph is used

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* remove unused quantization code and enable awq/gptq int4

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix gptq issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* enable fp8

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* warmup prefill

remove model where pageattn is not used, set block table to None since it's not used

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* add warmup_decode

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* warmup decode

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* remove block_tables and prefill_cache_indices which will lead to dynamic shape

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix comment

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* missing gptj change...

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix some issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* remove torch.where to fix incorrect output in hpu graph model

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* match the latest vllm_extension ops

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

---------

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
2025-04-14 15:58:13 +02:00

72 lines
2.3 KiB
Rust

use std::fmt;
use std::process::Command;
pub(crate) struct Env {
cargo_target: &'static str,
cargo_version: &'static str,
git_sha: &'static str,
docker_label: &'static str,
nvidia_env: String,
xpu_env: String,
hpu_env: String,
}
impl Env {
pub fn new() -> Self {
let nvidia_env = nvidia_smi();
let xpu_env = xpu_smi();
let hpu_env = hl_smi();
Self {
nvidia_env: nvidia_env.unwrap_or("N/A".to_string()),
xpu_env: xpu_env.unwrap_or("N/A".to_string()),
hpu_env: hpu_env.unwrap_or("N/A".to_string()),
cargo_target: env!("VERGEN_CARGO_TARGET_TRIPLE"),
cargo_version: env!("VERGEN_RUSTC_SEMVER"),
git_sha: option_env!("VERGEN_GIT_SHA").unwrap_or("N/A"),
docker_label: option_env!("DOCKER_LABEL").unwrap_or("N/A"),
}
}
pub fn should_start_a_single_hpu_shard(&self) -> bool {
self.hpu_env != "N/A" && std::env::var("ATTENTION").as_deref() != Ok("paged")
}
}
impl fmt::Display for Env {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
writeln!(f, "Runtime environment:")?;
writeln!(f, "Target: {}", self.cargo_target)?;
writeln!(f, "Cargo version: {}", self.cargo_version)?;
writeln!(f, "Commit sha: {}", self.git_sha)?;
writeln!(f, "Docker label: {}", self.docker_label)?;
writeln!(f, "nvidia-smi:\n{}", self.nvidia_env)?;
writeln!(f, "xpu-smi:\n{}", self.xpu_env)?;
writeln!(f, "hpu-smi:\n{}", self.hpu_env)?;
Ok(())
}
}
fn nvidia_smi() -> Option<String> {
let output = Command::new("nvidia-smi").output().ok()?;
let nvidia_smi = String::from_utf8(output.stdout).ok()?;
let output = nvidia_smi.replace('\n', "\n ");
Some(output.trim().to_string())
}
fn xpu_smi() -> Option<String> {
let output = Command::new("xpu-smi").arg("discovery").output().ok()?;
let xpu_smi = String::from_utf8(output.stdout).ok()?;
let output = xpu_smi.replace('\n', "\n ");
Some(output.trim().to_string())
}
fn hl_smi() -> Option<String> {
let output = Command::new("hl-smi").output().ok()?;
let hl_smi = String::from_utf8(output.stdout).ok()?;
let output = hl_smi.replace('\n', "\n ");
Some(output.trim().to_string())
}