20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[SpecDecoding] Update MLPSpeculator CI tests to use smaller model (#6714)

Browse Source
This commit is contained in:
Nick Hill 2024-07-24 00:34:22 -07:00 committed by GitHub
parent 5e8ca973eb
commit c882a7f5b3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/spec_decode/e2e/test_mlp_correctness.py
View File

@ -24,14 +24,14 @@ import pytest
from .conftest import run_greedy_equality_correctness_test from .conftest import run_greedy_equality_correctness_test
# main model # main model
MAIN_MODEL = "ibm-granite/granite-3b-code-instruct" MAIN_MODEL = "JackFram/llama-160m"
# speculative model # speculative model
SPEC_MODEL = "ibm-granite/granite-3b-code-instruct-accelerator" SPEC_MODEL = "ibm-fms/llama-160m-accelerator"
# max. number of speculative tokens: this corresponds to # max. number of speculative tokens: this corresponds to
# n_predict in the config.json of the speculator model. # n_predict in the config.json of the speculator model.
MAX_SPEC_TOKENS = 5 MAX_SPEC_TOKENS = 3
# precision # precision
PRECISION = "float32" PRECISION = "float32"