Remove all2all backend envvar (#30363)

Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Elizabeth Thomas
2025-12-18 19:46:28 +00:00
committed by GitHub
co-authored by Harry Mellor
parent 97000a2be7
commit 41b6f9200f
12 changed files with 40 additions and 43 deletions
@@ -55,7 +55,6 @@ done
echo "Starting vLLM server for $MODEL_NAME with data parallel size: $DATA_PARALLEL_SIZE and redundant experts: $REDUNDANT_EXPERTS"
export RAY_DEDUP_LOGS=0
export VLLM_ALL2ALL_BACKEND="pplx"
export VLLM_USE_DEEP_GEMM=1
vllm serve $MODEL_NAME \
@@ -65,6 +64,7 @@ vllm serve $MODEL_NAME \
--enforce-eager \
--enable-expert-parallel \
--enable-eplb \
--all2all-backend pplx \
--num-redundant-experts $REDUNDANT_EXPERTS \
--trust-remote-code \
--host $HOST \