use new upstream branches for nd-parallelism

This commit is contained in:
Wing Lian
2025-07-22 21:12:22 -04:00
parent 5f1a4306b0
commit 5c74bebfd0
22 changed files with 134 additions and 95 deletions

View File

@@ -67,7 +67,7 @@ class TestSequenceParallelism:
"logging_steps": 1,
"weight_decay": 0.0,
"use_tensorboard": True,
"sequence_parallel_degree": 2,
"context_parallel_size": 2,
"ring_attn_func": ring_attn_func,
"save_first_step": False,
}