Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
47 lines
1.1 KiB
Bash
Executable File
47 lines
1.1 KiB
Bash
Executable File
#!/bin/bash
|
|
# We can use this script to compute baseline accuracy on GSM for transformers.
|
|
#
|
|
# Make sure you have lm-eval-harness installed:
|
|
# pip install "lm-eval[api]>=0.4.11"
|
|
|
|
usage() {
|
|
echo``
|
|
echo "Runs lm eval harness on GSM8k using huggingface transformers."
|
|
echo "This pathway is intended to be used to create baselines for "
|
|
echo "our automated nm-test-accuracy workflow"
|
|
echo
|
|
echo "usage: ${0} <options>"
|
|
echo
|
|
echo " -m - huggingface stub or local directory of the model"
|
|
echo " -b - batch size to run the evaluation at"
|
|
echo " -l - limit number of samples to run"
|
|
echo " -f - number of fewshot samples to use"
|
|
echo
|
|
}
|
|
|
|
while getopts "m:b:l:f:" OPT; do
|
|
case ${OPT} in
|
|
m )
|
|
MODEL="$OPTARG"
|
|
;;
|
|
b )
|
|
BATCH_SIZE="$OPTARG"
|
|
;;
|
|
l )
|
|
LIMIT="$OPTARG"
|
|
;;
|
|
f )
|
|
FEWSHOT="$OPTARG"
|
|
;;
|
|
\? )
|
|
usage
|
|
exit 1
|
|
;;
|
|
esac
|
|
done
|
|
|
|
lm_eval --model hf \
|
|
--model_args "pretrained=$MODEL,parallelize=True" \
|
|
--tasks gsm8k --num_fewshot "$FEWSHOT" --limit "$LIMIT" \
|
|
--batch_size "$BATCH_SIZE"
|