Unsloth chat template for qwen3.5

This commit is contained in:
Eugene Rakhmatulin
2026-03-06 23:35:18 -08:00
parent 9dc09bd04b
commit d42c4199fa
5 changed files with 166 additions and 1 deletions

View File

@@ -17,6 +17,7 @@ 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-coder-next
- mods/fix-qwen3.5-chat-template
# Default settings (can be overridden via CLI)
defaults:
@@ -45,5 +46,6 @@ command: |
--load-format fastsafetensors \
--attention-backend flashinfer \
--enable-prefix-caching \
--chat-template unsloth.jinja \
-tp {tensor_parallel} \
--distributed-executor-backend ray