[Compile] Remove torch.compile-based sequence parallelism and AsyncTP (#60517)

This commit is contained in:
Woosuk Kwon
2026-10-08 08:28:23 -07:00
committed by GitHub
parent 072d49bb6e
commit 194bd72be7
34 changed files with 32 additions and 4797 deletions
-1
View File
@@ -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,