149 lines
4.4 KiB
Python
149 lines
4.4 KiB
Python
"""DSV4 Flash PD-disagg with NIXL backend. Both sides run dp-attention
|
|
+ deepep + EAGLE MTP so attn_tp_size and the V4 state pool layout are
|
|
fully symmetric: same SWA item_len under matching attn_tp, and same
|
|
DSA c4/c128 indexer ring buffer size under matching spec status. nixl
|
|
`send_state` is page-by-index and has no V4 TP-slice / spec-asymmetric
|
|
path, so any layout mismatch would trip the item_len assert in
|
|
`nixl/conn.py`."""
|
|
|
|
import unittest
|
|
from types import SimpleNamespace
|
|
|
|
from sglang.test.few_shot_gsm8k import run_eval as run_gsm8k_eval
|
|
from sglang.test.server_fixtures.disaggregation_fixture import (
|
|
PDDisaggregationServerBase,
|
|
)
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
popen_launch_pd_server,
|
|
)
|
|
|
|
DSV4_FLASH_MODEL_PATH = "sgl-project/DeepSeek-V4-Flash-FP8"
|
|
|
|
DSV4_FLASH_ENV = {
|
|
"SGLANG_DSV4_FP4_EXPERTS": "0",
|
|
# MTP num_draft_tokens=4 scales dispatch by ~4x; 256 overflows at bs=128.
|
|
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "1024",
|
|
}
|
|
|
|
DEEPEP_CONFIG = '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
|
|
|
|
|
|
class TestDSV4FlashPDDisaggNIXL(PDDisaggregationServerBase):
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
super().setUpClass()
|
|
cls.transfer_backend = ["--disaggregation-transfer-backend", "nixl"]
|
|
cls.rdma_devices = []
|
|
cls.model = DSV4_FLASH_MODEL_PATH
|
|
|
|
cls.start_prefill()
|
|
cls.start_decode()
|
|
|
|
cls.wait_server_ready(cls.prefill_url + "/health", process=cls.process_prefill)
|
|
cls.wait_server_ready(cls.decode_url + "/health", process=cls.process_decode)
|
|
cls.launch_lb()
|
|
|
|
@classmethod
|
|
def start_prefill(cls):
|
|
prefill_args = [
|
|
"--trust-remote-code",
|
|
"--disaggregation-mode",
|
|
"prefill",
|
|
"--base-gpu-id",
|
|
"0",
|
|
"--tp",
|
|
"4",
|
|
"--dp",
|
|
"4",
|
|
"--enable-dp-attention",
|
|
"--moe-a2a-backend",
|
|
"deepep",
|
|
"--deepep-config",
|
|
DEEPEP_CONFIG,
|
|
"--cuda-graph-max-bs-decode",
|
|
"128",
|
|
"--max-running-requests",
|
|
"256",
|
|
"--mem-fraction-static",
|
|
"0.7",
|
|
"--speculative-algorithm",
|
|
"EAGLE",
|
|
"--speculative-num-steps",
|
|
"3",
|
|
"--speculative-eagle-topk",
|
|
"1",
|
|
"--speculative-num-draft-tokens",
|
|
"4",
|
|
*cls.transfer_backend,
|
|
*cls.rdma_devices,
|
|
]
|
|
cls.process_prefill = popen_launch_pd_server(
|
|
cls.model,
|
|
cls.prefill_url,
|
|
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
other_args=prefill_args,
|
|
env=DSV4_FLASH_ENV,
|
|
)
|
|
|
|
@classmethod
|
|
def start_decode(cls):
|
|
decode_args = [
|
|
"--trust-remote-code",
|
|
"--disaggregation-mode",
|
|
"decode",
|
|
"--base-gpu-id",
|
|
"4",
|
|
"--tp",
|
|
"4",
|
|
"--dp",
|
|
"4",
|
|
"--enable-dp-attention",
|
|
"--moe-a2a-backend",
|
|
"deepep",
|
|
"--deepep-config",
|
|
DEEPEP_CONFIG,
|
|
"--cuda-graph-max-bs-decode",
|
|
"128",
|
|
"--max-running-requests",
|
|
"256",
|
|
"--mem-fraction-static",
|
|
"0.7",
|
|
"--speculative-algorithm",
|
|
"EAGLE",
|
|
"--speculative-num-steps",
|
|
"3",
|
|
"--speculative-eagle-topk",
|
|
"1",
|
|
"--speculative-num-draft-tokens",
|
|
"4",
|
|
*cls.transfer_backend,
|
|
*cls.rdma_devices,
|
|
]
|
|
cls.process_decode = popen_launch_pd_server(
|
|
cls.model,
|
|
cls.decode_url,
|
|
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
other_args=decode_args,
|
|
env=DSV4_FLASH_ENV,
|
|
)
|
|
|
|
def test_gsm8k(self):
|
|
"""End-to-end PD-disagg accuracy through the LB."""
|
|
args = SimpleNamespace(
|
|
num_shots=5,
|
|
data_path=None,
|
|
num_questions=200,
|
|
max_new_tokens=512,
|
|
parallel=64,
|
|
host=f"http://{self.base_host}",
|
|
port=int(self.lb_port),
|
|
)
|
|
metrics = run_gsm8k_eval(args)
|
|
print(f"{metrics=}")
|
|
self.assertGreater(metrics["accuracy"], 0.95)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|