[Auto Sync] optionally disable fake register in Update fp8_kernel.py (20251202) (#14255)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: gauravjain14 <41287729+gauravjain14@users.noreply.github.com>

python/sglang/srt/layers/quantization/fp8_kernel.py

@@ -1854,6 +1854,10 @@ if _is_cuda:
         ):
             return
 
-    @torch.library.register_fake("sgl_kernel::sgl_per_token_quant_fp8")
-    def _(input, output_q, output_s):
-        return
+    # FIXME: for some models, this fake registration will cause NaN outputs.
+    # So we gate the fake registration with an environment variable for them.
+    if not get_bool_env_var("SGLANG_DISABLE_SGL_KERNEL_FAKE_REGISTER"):
+
+        @torch.library.register_fake("sgl_kernel::sgl_per_token_quant_fp8")
+        def _(input, output_q, output_s):
+            return