Renamed recipe for qwen3.5-35b-a3b-fp8 to match others
This commit is contained in:
@@ -24,7 +24,7 @@ defaults:
|
||||
host: 0.0.0.0
|
||||
tensor_parallel: 2
|
||||
gpu_memory_utilization: 0.7
|
||||
max_model_len: 131072
|
||||
max_model_len: 262144
|
||||
max_num_batched_tokens: 16384
|
||||
|
||||
# Environment variables
|
||||
Reference in New Issue
Block a user