huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Easier quantization.

Browse Source
This commit is contained in:
Nicolas Patry 2023-05-04 14:25:24 +02:00
parent e2d167256a
commit 4882de4d7a
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/cli.py
View File

@ -61,7 +61,9 @@ def serve(
if otlp_endpoint is not None: if otlp_endpoint is not None:
setup_tracing(shard=os.getenv("RANK", 0), otlp_endpoint=otlp_endpoint) setup_tracing(shard=os.getenv("RANK", 0), otlp_endpoint=otlp_endpoint)
server.serve(model_id, revision, sharded, quantize.value, uds_path) # Downgrade enum into str for easier management later on
quantize = None if quantize is None else quantize.value
server.serve(model_id, revision, sharded, quantize, uds_path)
@app.command() @app.command()