huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Tmp dump (sending real image for real memory offset to be computed.

Browse Source
This commit is contained in:
Nicolas Patry 2024-04-09 05:15:09 +00:00
parent 274b68ad7d
commit 215030ac88
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
router/client/src/client.rs
View File

@ -112,10 +112,12 @@ impl Client {
// Create requests // Create requests
while n_tokens < max_prefill_tokens { while n_tokens < max_prefill_tokens {
let truncate = min(max_input_length, max_prefill_tokens - n_tokens); let truncate = min(max_input_length, max_prefill_tokens - n_tokens);
let mut inputs = "_test ".to_string().repeat(max_input_length as usize);
inputs.push_str("![](data:image/jpeg;base64,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");
requests.push(Request { requests.push(Request {
id: 0, id: 0,
// We truncate the input on the server side to be sure that it has the correct size // We truncate the input on the server side to be sure that it has the correct size
inputs: "_test ".to_string().repeat(max_input_length as usize), inputs,
truncate, truncate,
// Set sampling parameters to also take these ops into account in the max memory // Set sampling parameters to also take these ops into account in the max memory
parameters: Some(NextTokenChooserParameters { parameters: Some(NextTokenChooserParameters {