migrate example configs to canonical attn_implementation

2026-04-23 22:15:07 +00:00
parent 2d64d009d8
commit 39226623d2
222 changed files with 209 additions and 243 deletions
--- a/examples/distributed-parallel/llama-3_1-8b-hsdp-tp.yaml
+++ b/examples/distributed-parallel/llama-3_1-8b-hsdp-tp.yaml
@@ -29,7 +29,7 @@ output_dir: ./outputs/ndp-out/

 sequence_len: 2048
 sample_packing: true
-flash_attention: true
+attn_implementation: flash_attention_2

 gradient_accumulation_steps: 1
 micro_batch_size: 1
--- a/examples/distributed-parallel/qwen3-8b-fsdp-tp-cp.yaml
+++ b/examples/distributed-parallel/qwen3-8b-fsdp-tp-cp.yaml
@@ -26,7 +26,7 @@ output_dir: ./outputs/ndp-out/

 sequence_len: 8192
 sample_packing: true
-flash_attention: true
+attn_implementation: flash_attention_2

 gradient_accumulation_steps: 1
 micro_batch_size: 1  # must be 1 when using context parallel