[Compile] Remove torch.compile-based sequence parallelism and AsyncTP (#60517)
This commit is contained in:
@@ -730,7 +730,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
attn_cg_support.min_cg_attn_backend,
|
||||
self.decode_query_len,
|
||||
use_v2_model_runner=True,
|
||||
tensor_parallel_size=self.parallel_config.tensor_parallel_size,
|
||||
kv_cache_config=self.kv_cache_config,
|
||||
max_num_reqs=self.max_num_reqs,
|
||||
is_profiling=is_profiling,
|
||||
|
||||
Reference in New Issue
Block a user