biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Fix various config related issues for Transformers v5 (#37681)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2026-03-20 16:30:12 +00:00
committed by GitHub
parent 2e089b96a8
commit 6ade4bc5a5
8 changed files with 42 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/entrypoints/openai/chat_completion/test_completion_with_function_calling.py
View File

@@ -231,13 +231,14 @@ def k2_server():
"--gpu-memory-utilization",
"0.4",
] + ROCM_EXTRA_ARGS
# hack to test kimi_k2 tool use tool_id format.
# avoid error in is_deepseek_mla check by setting kv_lora_rank=null
# Test kimi_k2 tool use tool_id format by overriding model_type.
# is_deepseek_mla safely returns False via getattr when kv_lora_rank
# is absent from the underlying config.
with RemoteOpenAIServer(
MODEL_NAME,
args,
env_dict=ROCM_ENV_OVERRIDES,
override_hf_configs={"model_type": "kimi_k2", "kv_lora_rank": None},
override_hf_configs={"model_type": "kimi_k2"},
) as remote_server:
yield remote_server