forked from ai-dynamo/dynamo
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathagg_flexkv_router.sh
More file actions
executable file
·53 lines (49 loc) · 2.04 KB
/
agg_flexkv_router.sh
File metadata and controls
executable file
·53 lines (49 loc) · 2.04 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
#!/bin/bash
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
set -e
trap 'echo Cleaning up...; kill 0' EXIT
MODEL="Qwen/Qwen3-0.6B"
HTTP_PORT="${DYN_HTTP_PORT:-8000}"
echo "=========================================="
echo "Launching Aggregated Serving + FlexKV + KV Routing (2 GPUs)"
echo "=========================================="
echo "Model: $MODEL"
echo "Frontend: http://localhost:$HTTP_PORT"
echo "=========================================="
echo ""
echo "Example test command:"
echo ""
echo " curl http://localhost:${HTTP_PORT}/v1/chat/completions \\"
echo " -H 'Content-Type: application/json' \\"
echo " -d '{"
echo " \"model\": \"${MODEL}\","
echo " \"messages\": [{\"role\": \"user\", \"content\": \"Explain why Roger Federer is considered one of the greatest tennis players of all time\"}],"
echo " \"max_tokens\": 32"
echo " }'"
echo ""
echo "=========================================="
# Run frontend and KV router
# dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000)
python -m dynamo.frontend \
--router-mode kv \
--router-reset-states &
# Run worker with FlexKV
DYNAMO_USE_FLEXKV=1 \
FLEXKV_CPU_CACHE_GB=32 \
FLEXKV_SERVER_RECV_PORT="ipc:///tmp/flexkv_server_0" \
CUDA_VISIBLE_DEVICES=0 \
python -m dynamo.vllm \
--model $MODEL \
--kv-transfer-config '{"kv_connector":"FlexKVConnectorV1","kv_role":"kv_both"}' \
--gpu-memory-utilization 0.2 \
--kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20080","enable_kv_cache_events":true}' &
DYNAMO_USE_FLEXKV=1 \
FLEXKV_CPU_CACHE_GB=32 \
FLEXKV_SERVER_RECV_PORT="ipc:///tmp/flexkv_server_1" \
CUDA_VISIBLE_DEVICES=1 \
python -m dynamo.vllm \
--model $MODEL \
--kv-transfer-config '{"kv_connector":"FlexKVConnectorV1","kv_role":"kv_both"}' \
--gpu-memory-utilization 0.2 \
--kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20081","enable_kv_cache_events":true}'