phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-10 03:30:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add completion() impl for meta-reference

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 20:41:21 -07:00
parent bcaf639dd6
commit 072d1b7205
4 changed files with 137 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/impls/meta_reference/inference/generation.py
View file

@ -301,6 +301,7 @@ class Llama:
request: CompletionRequest,
) -> Generator:
sampling_params = request.sampling_params
max_gen_len = sampling_params.max_tokens
if (
max_gen_len is None
or max_gen_len == 0
@ -315,6 +316,7 @@ class Llama:
temperature=sampling_params.temperature,
top_p=sampling_params.top_p,
logprobs=bool(request.logprobs),
include_stop_token=True,
echo=False,
)