[Config Refactor] Migrate Ming and Ming-TTS deploy/pipline configs (#3154)

Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Yuanheng ZhaoandHongsheng Liu authored and GitHub committed 2026-05-03 14:43:49 +12:00
1 parent 6a837849dd
commit d49356e4ca
25 files changed
+518 -398

No files matched your search

+46
View File
@@ -484,6 +484,52 @@ _CI_OVERLAYS: dict[str, dict[str, Any]] = {
},
},
},
"ming_flash_omni": {
"base_config": "ming_flash_omni.yaml",
"stages": [
{
"stage_id": 0,
"max_num_seqs": 1,
"gpu_memory_utilization": 0.74,
"max_model_len": 16384,
"max_num_batched_tokens": 16384,
"mm_processor_cache_gb": 0,
"skip_mm_profiling": True,
"enable_flashinfer_autotune": False,
"load_format": "dummy",
"default_sampling_params": {
"temperature": 0.0,
"max_tokens": 100,
},
},
{
"stage_id": 1,
"max_num_seqs": 1,
"gpu_memory_utilization": 0.18,
"load_format": "dummy",
},
],
},
"ming_flash_omni_thinker_only": {
"base_config": "ming_flash_omni_thinker_only.yaml",
"stages": [
{
"stage_id": 0,
"max_num_seqs": 1,
"gpu_memory_utilization": 0.9,
"max_model_len": 16384,
"max_num_batched_tokens": 16384,
"mm_processor_cache_gb": 0,
"skip_mm_profiling": True,
"enable_flashinfer_autotune": False,
"load_format": "dummy",
"default_sampling_params": {
"temperature": 0.4,
"max_tokens": 100,
},
},
],
},
# Single-stage thinker-only topology for the abort test.
"qwen2_5_omni_thinker_only": {
"async_chunk": False,