cjw/rocm_vllm_nightly
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

x

Browse Source
This commit is contained in:
chenjw28
2026-06-02 17:17:32 +08:00
parent f2c3445113
commit 76dd476019
1 changed files with 15 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/model_catalog.py
+15 -3
View File
@@ -68,6 +68,18 @@ def resolve_runtime_settings(content: dict[str, Any]) -> dict[str, Any]:
internal_url = _to_str(content.get("vllm_openai_internal_url")) internal_url = _to_str(content.get("vllm_openai_internal_url"))
if not internal_url: if not internal_url:
internal_url = f"http://127.0.0.1:{openai_port}/v1" internal_url = f"http://127.0.0.1:{openai_port}/v1"
enable_thinking_env = os.getenv("VLLM_ENABLE_THINKING")
if enable_thinking_env is not None:
default_enable_thinking = _to_bool(enable_thinking_env, False)
else:
default_enable_thinking = _to_bool(content.get("default_enable_thinking"), False)
reasoning_enabled_env = os.getenv("VLLM_REASONING_ENABLED")
if reasoning_enabled_env is not None:
reasoning_enabled = _to_bool(reasoning_enabled_env, False)
else:
reasoning_enabled = _to_bool(content.get("reasoning_enabled"), False)
return { return {
"host": str(api_service.get("host", "0.0.0.0")), "host": str(api_service.get("host", "0.0.0.0")),
"port": _to_int(api_service.get("port"), 8000), "port": _to_int(api_service.get("port"), 8000),
@@ -75,9 +87,9 @@ def resolve_runtime_settings(content: dict[str, Any]) -> dict[str, Any]:
"openai_port": openai_port, "openai_port": openai_port,
"vllm_openai_internal_url": internal_url.rstrip("/"), "vllm_openai_internal_url": internal_url.rstrip("/"),
"public_model_name": _to_str(content.get("public_model_name"), "Qwen_local_model"), "public_model_name": _to_str(content.get("public_model_name"), "Qwen_local_model"),
"default_enable_thinking": _to_bool(content.get("default_enable_thinking"), False), "default_enable_thinking": default_enable_thinking,
"api_key": str(content.get("api_key", "")).strip() or None, "api_key": str(content.get("api_key", "")).strip() or None,
"reasoning_enabled": _to_bool(content.get("reasoning_enabled"), False), "reasoning_enabled": reasoning_enabled,
"tensor_parallel_size": _to_int(content.get("tensor_parallel_size"), 2), "tensor_parallel_size": _to_int(content.get("tensor_parallel_size"), 2),
"dtype": str(content.get("dtype", "bfloat16")), "dtype": str(content.get("dtype", "bfloat16")),
"revision": str(content.get("revision", "")).strip() or None, "revision": str(content.get("revision", "")).strip() or None,
@@ -125,7 +137,7 @@ def resolve_model_profile(
"dtype": _to_str(profile.get("dtype")), "dtype": _to_str(profile.get("dtype")),
"quantization": _to_str(profile.get("quantization")), "quantization": _to_str(profile.get("quantization")),
"model_impl": _to_str(profile.get("model_impl")), "model_impl": _to_str(profile.get("model_impl")),
"reasoning_parser": _to_str(profile.get("reasoning_parser")), "reasoning_parser": _to_str(os.getenv("VLLM_REASONING_PARSER") or profile.get("reasoning_parser")),
"max_model_len": _to_int(profile.get("ctx"), 8192), "max_model_len": _to_int(profile.get("ctx"), 8192),
"max_num_seqs": _to_int(profile.get("max_num_seqs"), 64), "max_num_seqs": _to_int(profile.get("max_num_seqs"), 64),
"max_tokens": _to_int(profile.get("max_tokens"), 4096), "max_tokens": _to_int(profile.get("max_tokens"), 4096),