icer/qwen36_01
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

test eager and custom allreduce toggles

Browse Source
This commit is contained in:
the magician
2026-07-14 19:18:46 +08:00
parent 82c1463b0c
commit a5abd66e21
7 changed files with 777 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/engine/arg_utils.py
View File

@@ -851,7 +851,7 @@ class EngineArgs:
max_model_len=self.max_model_len,
quantization=self.quantization,
quantization_param_path=self.quantization_param_path,
enforce_eager=True,
enforce_eager=self.enforce_eager,
max_context_len_to_capture=self.max_context_len_to_capture,
max_seq_len_to_capture=self.max_seq_len_to_capture,
max_logprobs=self.max_logprobs,
@@ -927,7 +927,7 @@ class EngineArgs:
tensor_parallel_size=self.tensor_parallel_size,
worker_use_ray=self.worker_use_ray,
max_parallel_loading_workers=self.max_parallel_loading_workers,
disable_custom_all_reduce=True,
disable_custom_all_reduce=self.disable_custom_all_reduce,
tokenizer_pool_config=TokenizerPoolConfig.create_config(
self.tokenizer_pool_size,
self.tokenizer_pool_type,