iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI][ROCm][Disagg] Add GLM-5.2-FP8 to MoRIIO model catalog (#53885)

Browse Source 
Signed-off-by: avininjamay8 <avpaul@amd.com>
Co-authored-by: avininjamay8 <avpaul@amd.com>
Co-authored-by: lcskrishna <lollachaitanya@gmail.com>
This commit is contained in:
Avinash Paul
2026-09-10 12:12:54 +08:00
committed by GitHub
co-authored by avininjamay8 lcskrishna
parent ea40bb9e90
commit 2a02f6efe3
2 changed files with 51 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/amd-disagg/models.yaml
+15
View File
@@ -104,3 +104,18 @@ models:
decode:
tp: "--gpu-memory-utilization 0.9"
ep: '--gpu-memory-utilization 0.75 --compilation-config {"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+quant_fp8"]}'
- model: GLM-5.2-FP8
env:
VLLM_ROCM_USE_AITER: "1"
VLLM_ROCM_USE_AITER_MLA: "1"
VLLM_ROCM_USE_AITER_MOE: "1"
VLLM_ROCM_USE_AITER_RMSNORM: "1"
VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS: "0"
base_flags: "--trust-remote-code --kv-cache-dtype fp8"
prefill:
tp: "--gpu-memory-utilization 0.85"
ep: "--gpu-memory-utilization 0.85 --enforce-eager"
decode:
tp: "--gpu-memory-utilization 0.85"
ep: '--gpu-memory-utilization 0.85 --compilation-config {"cudagraph_mode":"PIECEWISE"}'
.buildkite/amd-disagg/pipeline-disagg.yaml
+36
View File
@@ -98,6 +98,24 @@ steps:
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 bash .buildkite/amd-disagg/run-slurm-disagg-test.sh
- label: "GLM-5.2-FP8-PD-1P1D-TP8-MoRIIO-proxy"
agents:
queue: amd_mi350_ainic
timeout_in_minutes: 180
concurrency: 2
concurrency_group: "amd-disagg/mi350/2node"
commands:
- MODEL_NAME=GLM-5.2-FP8 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: "GLM-5.2-FP8-PD-1P1D-TP8-MoRIIO-vllm-router"
agents:
queue: amd_mi350_ainic
timeout_in_minutes: 180
concurrency: 2
concurrency_group: "amd-disagg/mi350/2node"
commands:
- MODEL_NAME=GLM-5.2-FP8 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"
@@ -281,3 +299,21 @@ steps:
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
- label: "GLM-5.2-FP8-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=GLM-5.2-FP8 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: "GLM-5.2-FP8-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=GLM-5.2-FP8 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