[Bugfix] Fix chat template loading (#15143)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Cyrus Leung
2025-03-24 21:50:09 +08:00
committed by GitHub
parent 038de04d7b
commit cbcdf2c609
7 changed files with 196 additions and 56 deletions

View File

@@ -39,7 +39,10 @@ def ensure_system_prompt(messages: list[dict[str, Any]],
# universal args for all models go here. also good if you need to test locally
# and change type or KV cache quantization or something.
ARGS: list[str] = ["--enable-auto-tool-choice", "--max-model-len", "1024"]
ARGS: list[str] = [
"--enable-auto-tool-choice", "--max-model-len", "1024", "--max-num-seqs",
"256"
]
CONFIGS: dict[str, ServerConfig] = {
"hermes": {