switching gpt-oss-120b to solo only for now
This commit is contained in:
@@ -11,6 +11,9 @@ model: openai/gpt-oss-120b
|
||||
# Container image to use
|
||||
container: vllm-node-mxfp4
|
||||
|
||||
# Only solo now
|
||||
solo_only: true
|
||||
|
||||
# Build arguments for build-and-copy.sh
|
||||
build_args:
|
||||
- --exp-mxfp4
|
||||
@@ -22,7 +25,7 @@ mods: []
|
||||
defaults:
|
||||
port: 8000
|
||||
host: 0.0.0.0
|
||||
tensor_parallel: 2
|
||||
tensor_parallel: 1
|
||||
gpu_memory_utilization: 0.70
|
||||
max_num_batched_tokens: 8192
|
||||
|
||||
@@ -37,8 +40,6 @@ command: |
|
||||
--tool-call-parser openai \
|
||||
--reasoning-parser openai_gptoss \
|
||||
--enable-auto-tool-choice \
|
||||
--tensor-parallel-size {tensor_parallel} \
|
||||
--distributed-executor-backend ray \
|
||||
--gpu-memory-utilization {gpu_memory_utilization} \
|
||||
--enable-prefix-caching \
|
||||
--load-format fastsafetensors \
|
||||
|
||||
Reference in New Issue
Block a user