alihan/text-generation-inference
1
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2023-08-23 10:47:54 +03:00
Code Issues Packages Projects Releases Wiki Activity

v0.1.0

Browse Source
This commit is contained in:
Olivier Dehaene
2022-10-18 15:19:03 +02:00
committed by OlivierDehaene
parent 92c1ecd008
commit f16f2f5ae1
36 changed files with 1556 additions and 677 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
proto/generate.proto
View File

@@ -11,10 +11,6 @@ service TextGenerationService {
rpc Generate (GenerateRequest) returns (GenerateResponse);
/// Generate tokens for a list of cached batches
rpc GenerateWithCache (GenerateWithCacheRequest) returns (GenerateWithCacheResponse);
/// Generate tokens until the text of at least one request of the batch is generated
rpc GenerateUntilFinished (GenerateUntilFinishedRequest) returns (GenerateUntilFinishedResponse);
/// Generate tokens until the text of at least one request of the cached batches i finished
rpc GenerateUntilFinishedWithCache (GenerateUntilFinishedWithCacheRequest) returns (GenerateUntilFinishedWithCacheResponse);
}
/// Empty request
@@ -92,27 +88,3 @@ message GenerateWithCacheResponse {
/// Next batch (cached)
optional Batch batch = 2;
}
message GenerateUntilFinishedRequest {
/// Batch
Batch batch = 1;
}
message GenerateUntilFinishedResponse {
/// Finished requests
repeated GeneratedText generated_texts = 1;
/// Next batch (cached)
optional Batch batch = 2;
}
message GenerateUntilFinishedWithCacheRequest {
/// Cached batches
repeated Batch batches = 1;
}
message GenerateUntilFinishedWithCacheResponse {
/// Finished requests
repeated GeneratedText generated_texts = 1;
/// Next batch (cached)
optional Batch batch = 2;
}