Update base for Update on "[Executorch] Add quantized kv cache to oss ci"

kimishpatel · kimishpatel · commit 317fa7c3052b · 2024-11-28T17:28:31.000-08:00
Fixes to make sure quantized kv cache works in oss Differential Revision: [D66269487](https://our.internmc.facebook.com/intern/diff/D66269487/) [ghstack-poisoned]
diff --git a/examples/models/llama/eval_llama_lib.py b/examples/models/llama/eval_llama_lib.py
@@ -102,7 +102,7 @@ def __init__(
 
         # Note: import this after portable_lib
         from executorch.extension.llm.custom_ops import (  # noqa
-            sdpa_with_kv_cache,  # usort: skip
+            custom_ops,  # usort: skip
         )
         from executorch.kernels import quantized  # noqa
 

Original file line number	Diff line number	Diff line change
`@@ -102,7 +102,7 @@ def __init__(`
`102`	`102`
`103`	`103`	`# Note: import this after portable_lib`
`104`	`104`	`from executorch.extension.llm.custom_ops import ( # noqa`
`105`		`- sdpa_with_kv_cache, # usort: skip`
	`105`	`+ custom_ops, # usort: skip`
`106`	`106`	`)`
`107`	`107`	`from executorch.kernels import quantized # noqa`
`108`	`108`