Fixed qwen3.6 recipes
This commit is contained in:
@@ -14,7 +14,6 @@ model: Qwen/Qwen3.6-35B-A3B-FP8
|
||||
# Container image to use
|
||||
container: vllm-node
|
||||
|
||||
# Mod required to fix slowness and crash in the cluster (tracking https://github.com/vllm-project/vllm/issues/33857)
|
||||
mods:
|
||||
- mods/fix-qwen3.6-chat-template
|
||||
|
||||
@@ -33,7 +32,7 @@ env:
|
||||
|
||||
# The vLLM serve command template
|
||||
command: |
|
||||
vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
|
||||
vllm serve Qwen/Qwen3.6-35B-A3B-FP8 \
|
||||
--host {host} \
|
||||
--port {port} \
|
||||
--max-model-len {max_model_len} \
|
||||
|
||||
Reference in New Issue
Block a user