File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change @@ -58,8 +58,7 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
5858--config config.yaml \
5959--gpu-memory-utilization 0.9 \
6060--tensor-parallel-size $TP \
61- --max-num-seqs 512 \
62- --disable-log-requests > $SERVER_LOG 2>&1 &
61+ --max-num-seqs 512 > $SERVER_LOG 2>&1 &
6362
6463SERVER_PID=$!
6564
Original file line number Diff line number Diff line change @@ -43,7 +43,6 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
4343--tool-call-parser kimi_k2 \
4444--compilation_config.pass_config.fuse_allreduce_rms true \
4545--trust-remote-code \
46- --disable-log-requests \
4746--no-enable-prefix-caching > $SERVER_LOG 2>&1 &
4847
4948SERVER_PID=$!
Original file line number Diff line number Diff line change @@ -45,8 +45,7 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
4545--tool-call-parser kimi_k2 \
4646--compilation_config.pass_config.fuse_allreduce_rms true \
4747--trust-remote-code \
48- --no-enable-prefix-caching \
49- --disable-log-requests > $SERVER_LOG 2>&1 &
48+ --no-enable-prefix-caching > $SERVER_LOG 2>&1 &
5049
5150SERVER_PID=$!
5251
Original file line number Diff line number Diff line change @@ -41,7 +41,6 @@ vllm serve $MODEL --port $PORT \
4141--gpu-memory-utilization 0.95 \
4242--max-model-len $MAX_MODEL_LEN \
4343--block-size=32 \
44- --disable-log-requests \
4544--no-enable-prefix-caching \
4645--trust-remote-code > $SERVER_LOG 2>&1 &
4746
You can’t perform that action at this time.
0 commit comments