Benchmark and Bugfix for GLM-Image (#3024)

Signed-off-by: JaredforReal <w13431838023@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Jared WenandHongsheng Liu authored and GitHub committed 2026-04-25 20:49:19 +08:00
1 parent 6b52db9e2b
commit 6e35bfbbae
18 files changed
+1836 -381

No files matched your search

+17
View File
@@ -1032,6 +1032,7 @@ class AsyncOmniEngine:
original_prompt = prompt
stage_type = self.stage_metadata[0].get("stage_type")
_preprocess_ms = 0.0
if stage_type != "diffusion" and not isinstance(prompt, EngineCoreRequest):
# Inject global_request_id into the raw prompt.
if isinstance(prompt, dict):
@@ -1041,6 +1042,7 @@ class AsyncOmniEngine:
_inject_global_id(item, request_id)
# Full input processing (tokenization, multimodal, etc.)
_t_preprocess = time.perf_counter()
request = self.input_processor.process_inputs(
request_id=request_id,
prompt=prompt,
@@ -1054,6 +1056,7 @@ class AsyncOmniEngine:
data_parallel_rank=data_parallel_rank,
resumable=resumable,
)
_preprocess_ms = (time.perf_counter() - _t_preprocess) * 1000.0
# TODO (Peiqi): add this for Qwen3-TTS only. Other models don't have
# additional_information field in the prompt.
request = _upgrade_to_omni_request(request, prompt)
@@ -1090,6 +1093,8 @@ class AsyncOmniEngine:
"original_prompt": original_prompt,
"sampling_params_list": effective_sampling_params_list,
"final_stage_id": final_stage_id,
"preprocess_ms": _preprocess_ms,
"enqueue_ts": time.perf_counter(),
}
def _enqueue_cfg_companions(
@@ -1316,6 +1321,7 @@ class AsyncOmniEngine:
"num_weight_load_threads": kwargs.get("num_weight_load_threads", 4),
"quantization": kwargs.get("quantization", None),
"enable_diffusion_pipeline_profiler": kwargs.get("enable_diffusion_pipeline_profiler", False),
"enable_ar_profiler": kwargs.get("enable_ar_profiler", False),
**(
{
"profiler_config": asdict(kwargs["profiler_config"])
@@ -1458,6 +1464,17 @@ class AsyncOmniEngine:
or cfg.engine_args.quantization_config is None
):
cfg.engine_args.quantization_config = quantization_config
# Inject profiler flags for diffusion stages
for profiler_key in (
"enable_diffusion_pipeline_profiler",
"enable_ar_profiler",
):
val = kwargs.get(profiler_key)
if val:
if not hasattr(cfg.engine_args, profiler_key) or not getattr(
cfg.engine_args, profiler_key, False
):
setattr(cfg.engine_args, profiler_key, val)
quantization = kwargs.get("quantization")
if quantization is not None:
if not hasattr(cfg.engine_args, "quantization") or cfg.engine_args.quantization is None: