|
|
|
@@ -11,192 +11,273 @@ steps:
|
|
|
|
|
- label: "DeepSeek-V3-PD-1P1D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-V3-PD-1P1D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-R1-MXFP4-PD-1P1D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-R1-MXFP4-PD-1P1D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.5-MXFP4-PD-1P1D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.5-MXFP4-PD-1P1D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.6-MXFP4-PD-1P1D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.6-MXFP4-PD-1P1D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "MiniMax-M3-MXFP8-PD-1P1D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "MiniMax-M3-MXFP8-PD-1P1D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
#-------------------------------------- mi350 · disagg 2P2D (TP8, 4 nodes) · SLURM --------------------------------------#
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-V3-PD-2P2D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-V3-PD-2P2D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-R1-MXFP4-PD-2P2D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-R1-MXFP4-PD-2P2D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.5-MXFP4-PD-2P2D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.5-MXFP4-PD-2P2D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.6-MXFP4-PD-2P2D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.6-MXFP4-PD-2P2D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "MiniMax-M3-MXFP8-PD-2P2D-TP8-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "MiniMax-M3-MXFP8-PD-2P2D-TP8-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 120
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/4node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 xP=2 yD=2 NODES=4 GPUS_PER_NODE=8 WIDE_EP_MODE=0 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
#-------------------------------------- mi350 · disagg wide-EP (disabled) --------------------------------------#
|
|
|
|
|
#-------------------------------------- mi350 · disagg wide-EP intranode (EP8/DP8, 2 nodes) · SLURM --------------------------------------#
|
|
|
|
|
|
|
|
|
|
# - label: "DeepSeek-V3-PD-1P1D-EP8/DP8-WideEP-MoRIIO-proxy"
|
|
|
|
|
# agents:
|
|
|
|
|
# queue: amd_mi350_ainic
|
|
|
|
|
# timeout_in_minutes: 120
|
|
|
|
|
# concurrency: 2
|
|
|
|
|
# concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
# commands:
|
|
|
|
|
# - IMAGE=vllm/vllm-openai-rocm:nightly MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 SLURM_TIME_LIMIT=02:00:00 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
- label: "DeepSeek-V3-PD-1P1D-EP8/DP8-WideEP-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-V3-PD-1P1D-EP8/DP8-WideEP-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-V3 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-R1-MXFP4-PD-1P1D-EP8/DP8-WideEP-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "DeepSeek-R1-MXFP4-PD-1P1D-EP8/DP8-WideEP-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=DeepSeek-R1-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.5-MXFP4-PD-1P1D-EP8/DP8-WideEP-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.5-MXFP4-PD-1P1D-EP8/DP8-WideEP-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.5-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.6-MXFP4-PD-1P1D-EP8/DP8-WideEP-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "Kimi-K2.6-MXFP4-PD-1P1D-EP8/DP8-WideEP-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=Kimi-K2.6-MXFP4 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "MiniMax-M3-MXFP8-PD-1P1D-EP8/DP8-WideEP-MoRIIO-proxy"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=proxy WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|
|
|
|
|
|
- label: "MiniMax-M3-MXFP8-PD-1P1D-EP8/DP8-WideEP-MoRIIO-vllm-router"
|
|
|
|
|
agents:
|
|
|
|
|
queue: amd_mi350_ainic
|
|
|
|
|
timeout_in_minutes: 180
|
|
|
|
|
concurrency: 2
|
|
|
|
|
concurrency_group: "amd-disagg/mi350/2node"
|
|
|
|
|
commands:
|
|
|
|
|
- MODEL_NAME=MiniMax-M3-MXFP8 NODES=2 GPUS_PER_NODE=8 WIDE_EP_MODE=1 MORIIO_READ_MODE=0 RUN_AFTER_HEALTH=accuracy ROUTER_TYPE=vllm-router WAIT=1 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
|
|
|
|
|