[DCP] Support Decode Context Parallel (DCP) for GQA with FlashAttention (#24864)

Signed-off-by: yuanyongjie.yyj <yuanyongjie.yyj@antgroup.com>
Signed-off-by: FENP <32334296+FENP@users.noreply.github.com>
Signed-off-by: Jaya Yuan <yuanyongjie.yyj@antgroup.com>

tests/distributed/test_context_parallel.py

@@ -204,17 +204,21 @@ def _compare_cp_with_tp(
 
 
 CP_TEXT_GENERATION_MODELS = {
-    # [MLA attention only]
     "deepseek-ai/DeepSeek-V2-Lite-Chat": [
         CPTestSettings.detailed(),
         CPTestSettings.detailed(tp_base=2),
     ],
+    "bigcode/gpt_bigcode-santacoder": [
+        CPTestSettings.detailed(),
+        CPTestSettings.detailed(tp_base=2),
+    ],
 }
 
 CP_TEST_MODELS = [
     # TODO support other models
     # [LANGUAGE GENERATION]
     "deepseek-ai/DeepSeek-V2-Lite-Chat",
+    "bigcode/gpt_bigcode-santacoder",
 ]