Merge remote-tracking branch 'origin/main' into dev/vllm-align
This commit is contained in:
commit
22e01c416b
39 files changed
+2763
-518
No files matched your search
@@ -192,15 +192,6 @@ class GPUARModelRunner(OmniGPUModelRunner):
|
||||
num_encoder_reqs=len(scheduler_output.scheduled_encoder_inputs),
|
||||
)
|
||||
|
||||
logger.debug(
|
||||
"Running batch with cudagraph_mode: %s, batch_descriptor: %s, "
|
||||
"should_ubatch: %s, num_tokens_across_dp: %s",
|
||||
cudagraph_mode,
|
||||
batch_desc,
|
||||
should_ubatch,
|
||||
num_tokens_across_dp,
|
||||
)
|
||||
|
||||
num_tokens_padded = batch_desc.num_tokens
|
||||
num_reqs_padded = batch_desc.num_reqs if batch_desc.num_reqs is not None else num_reqs
|
||||
ubatch_slices, ubatch_slices_padded = maybe_create_ubatch_slices(
|
||||
@@ -211,12 +202,6 @@ class GPUARModelRunner(OmniGPUModelRunner):
|
||||
self.parallel_config.num_ubatches,
|
||||
)
|
||||
|
||||
logger.debug(
|
||||
"ubatch_slices: %s, ubatch_slices_padded: %s",
|
||||
ubatch_slices,
|
||||
ubatch_slices_padded,
|
||||
)
|
||||
|
||||
pad_attn = cudagraph_mode == CUDAGraphMode.FULL
|
||||
|
||||
use_spec_decode = len(scheduler_output.scheduled_spec_decode_tokens) > 0
|
||||
@@ -313,15 +298,6 @@ class GPUARModelRunner(OmniGPUModelRunner):
|
||||
aux_hidden_states = None
|
||||
|
||||
hidden_states, multimodal_outputs = self.extract_multimodal_outputs(model_output)
|
||||
if multimodal_outputs is not None:
|
||||
keys_or_type = (
|
||||
list(multimodal_outputs.keys())
|
||||
if isinstance(multimodal_outputs, dict)
|
||||
else type(multimodal_outputs)
|
||||
)
|
||||
logger.debug(f"[AR] execute_model: multimodal_outputs keys = {keys_or_type}")
|
||||
else:
|
||||
logger.debug("[AR] execute_model: multimodal_outputs is None")
|
||||
|
||||
if not self.broadcast_pp_output:
|
||||
# Common case.
|
||||
|
||||
Reference in new issue
Block a user