mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
Eric BuehlerandGitHub
a562fd0707
* Initial steps toward supporting deepseekv2 * Implement the attention forward * Add the mlp * Implement the moe gate and forward * Fixes * Forward pass runs * Clippy * Update * It works * Use faster rope * Use normal cache * Add framework for paged attn * Fixes * Support isq * Add moqe support, residual tensors * Add examples, python API, docs * Fix tests * Update deps
35 lines
1006 B
Rust
35 lines
1006 B
Rust
use anyhow::Result;
|
|
use mistralrs::{
|
|
IsqType, PagedAttentionMetaBuilder, TextMessageRole, TextMessages, TextModelBuilder,
|
|
};
|
|
|
|
#[tokio::main]
|
|
async fn main() -> Result<()> {
|
|
let model = TextModelBuilder::new("deepseek-ai/DeepSeek-V2-Lite")
|
|
.with_isq(IsqType::Q4K)
|
|
.with_logging()
|
|
.with_paged_attn(|| PagedAttentionMetaBuilder::default().build())?
|
|
.build()
|
|
.await?;
|
|
|
|
let messages = TextMessages::new()
|
|
.add_message(
|
|
TextMessageRole::System,
|
|
"You are an AI agent with a specialty in programming.",
|
|
)
|
|
.add_message(
|
|
TextMessageRole::User,
|
|
"Hello! How are you? Please write generic binary search function in Rust.",
|
|
);
|
|
|
|
let response = model.send_chat_request(messages).await?;
|
|
|
|
println!("{}", response.choices[0].message.content.as_ref().unwrap());
|
|
dbg!(
|
|
response.usage.avg_prompt_tok_per_sec,
|
|
response.usage.avg_compl_tok_per_sec
|
|
);
|
|
|
|
Ok(())
|
|
}
|