software-engineering/spark-vllm-docker
2
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity

Updated tests

Browse Source
This commit is contained in:
Eugene Rakhmatulin
2026-02-04 12:06:30 -08:00
parent c7d45157e0
commit f139c4b55d
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/expected_commands.sh
View File

@@ -23,7 +23,7 @@ GLM_FLASH_AWQ_ARGS=(
"--max-num-batched-tokens 4096"
"--max-num-seqs 64"
"--gpu-memory-utilization 0.7"
"--port 8888"
"--port 8000"
"--host 0.0.0.0"
)
@@ -34,7 +34,7 @@ GLM_FLASH_AWQ_ARGS=(
GPT_OSS_MODEL="openai/gpt-oss-120b"
GPT_OSS_CONTAINER="vllm-node-mxfp4"
GPT_OSS_ARGS=(
"--port 8888"
"--port 8000"
"--host 0.0.0.0"
"--enable-auto-tool-choice"
"--tool-call-parser openai"