Skip to content

GitLab

Unverified Commit a6d970e9 authored by Schwinn Saereesitthipitak's avatar Schwinn Saereesitthipitak Committed by GitHub
Browse files

feat: refactor GMS client memory manager with tiered API (#6549)

parent 651ef5b5
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
tests/fault_tolerance/gpu_memory_service/utils/sglang.py
View file @ a6d970e9
...@@ -44,7 +44,7 @@ class SGLangWithGMSProcess(ManagedProcess): ...@@ -44,7 +44,7 @@ class SGLangWithGMSProcess(ManagedProcess):
"gms", "gms",
"--enable-memory-saver", "--enable-memory-saver",
"--mem-fraction-static", "--mem-fraction-static",
"0.8", "0.9",
"--port", "--port",
str(sglang_port), str(sglang_port),
], ],
......
tests/fault_tolerance/gpu_memory_service/utils/vllm.py
View file @ a6d970e9
...@@ -54,7 +54,7 @@ class VLLMWithGMSProcess(ManagedProcess): ...@@ -54,7 +54,7 @@ class VLLMWithGMSProcess(ManagedProcess):
"gms", "gms",
"--enable-sleep-mode", "--enable-sleep-mode",
"--gpu-memory-utilization", "--gpu-memory-utilization",
"0.8", "0.9",
"--kv-events-config", "--kv-events-config",
kv_events_cfg, kv_events_cfg,
], ],
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment