Deepseek V4 (#23882)

Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: yueming-yuan <yym022502@gmail.com>
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Qiaolin Yu <90088090+qiaolin-yu@users.noreply.github.com>
Co-authored-by: Ethan (Yusheng) Su <11704492+yushengsu-thu@users.noreply.github.com>
Co-authored-by: Mingyi <27337995+wisclmy0611@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Yihao Wang <42559837+againstentropy@users.noreply.github.com>

test/manual/dsv4/test_dsv4_flash_sanity_tp8.py

@@ -0,0 +1,50 @@
+"""DSV4-Flash 8-GPU server sanity (TP8, no spec decoding)."""
+
+import unittest
+
+from sglang.srt.utils import kill_process_tree
+from sglang.test.kits.server_sanity_kit import ServerSanityMixin
+from sglang.test.test_utils import (
+    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+    DEFAULT_URL_FOR_TEST,
+    CustomTestCase,
+    popen_launch_server,
+)
+
+DSV4_FLASH_MODEL_PATH = "sgl-project/DeepSeek-V4-Flash-FP8"
+
+DSV4_FLASH_ENV = {
+    "SGLANG_DSV4_FP4_EXPERTS": "0",
+    "SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "1024",
+}
+
+
+class TestDSV4FlashTP8NoSpec(ServerSanityMixin, CustomTestCase):
+    """TP8, no spec decoding."""
+
+    @classmethod
+    def setUpClass(cls):
+        cls.base_url = DEFAULT_URL_FOR_TEST
+        cls.process = popen_launch_server(
+            DSV4_FLASH_MODEL_PATH,
+            cls.base_url,
+            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+            other_args=[
+                "--trust-remote-code",
+                "--tp",
+                "8",
+                "--max-running-requests",
+                "8",
+                "--mem-fraction-static",
+                "0.85",
+            ],
+            env=DSV4_FLASH_ENV,
+        )
+
+    @classmethod
+    def tearDownClass(cls):
+        kill_process_tree(cls.process.pid)
+
+
+if __name__ == "__main__":
+    unittest.main()