minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Refactor] Rename NSA → DSA: user-facing aliases, file/class/import rename (#25821)

Browse Source 
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Cheng Wan
2026-05-20 00:18:04 -07:00
committed by GitHub
co-authored by Claude Sonnet 4.6
parent da6d549ab2
commit 8131641bc6
162 changed files with 11298 additions and 10740 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/manual/dsv4/test_b200_flash.py
+2 -2
View File
@@ -87,8 +87,8 @@ class TestB200FlashCP(DSV4FlashAime25TestBase):
"4",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/dsv4/test_b200_pro.py
+2 -2
View File
@@ -101,8 +101,8 @@ class TestB200ProCP(DSV4ProAime25TestBase):
"8",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/dsv4/test_b300_flash.py
+2 -2
View File
@@ -89,8 +89,8 @@ class TestB300FlashCP(DSV4FlashAime25TestBase):
"4",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/dsv4/test_b300_pro.py
+2 -2
View File
@@ -103,8 +103,8 @@ class TestB300ProCP(DSV4ProAime25TestBase):
"8",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/dsv4/test_dsv4_pd_disagg_nixl.py
+1 -1
View File
@@ -1,7 +1,7 @@
"""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
NSA c4/c128 indexer ring buffer size under matching spec status. nixl
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`."""
test/manual/dsv4/test_gb300_flash.py
+2 -2
View File
@@ -87,8 +87,8 @@ class TestGB300FlashCP(DSV4FlashAime25TestBase):
"4",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/dsv4/test_gb300_pro.py
+2 -2
View File
@@ -103,8 +103,8 @@ class TestGB300ProCP(DSV4ProAime25TestBase):
"4",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/dsv4/test_h200_fp8_flash.py
+2 -2
View File
@@ -98,8 +98,8 @@ class TestH200Fp8FlashCP(DSV4FlashAime25TestBase):
"4",
"--moe-a2a-backend",
"deepep",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--chunked-prefill-size",
"16384",
test/manual/layers/attention/nsa/test_act_quant_triton.py → test/manual/layers/attention/dsa/test_act_quant_triton.py
+2 -2
View File
@@ -9,8 +9,8 @@ from typing import Tuple
import pytest
import torch
from sglang.srt.layers.attention.nsa.tilelang_kernel import act_quant
from sglang.srt.layers.attention.nsa.triton_kernel import act_quant as act_quant_triton
from sglang.srt.layers.attention.dsa.tilelang_kernel import act_quant
from sglang.srt.layers.attention.dsa.triton_kernel import act_quant as act_quant_triton
def benchmark_kernel(
test/manual/layers/attention/nsa/test_get_k_scale_triton_kernel.py → test/manual/layers/attention/dsa/test_get_k_scale_triton_kernel.py
+1 -1
View File
@@ -1,6 +1,6 @@
import torch
from sglang.srt.layers.attention.nsa.index_buf_accessor import (
from sglang.srt.layers.attention.dsa.index_buf_accessor import (
_get_k_and_s_triton_kernel,
)
test/manual/layers/attention/nsa/test_index_buf_accessor.py → test/manual/layers/attention/dsa/test_index_buf_accessor.py
+18 -18
View File
@@ -1,5 +1,5 @@
"""
Correctness tests for NSA Indexer K/S Buffer Access with Fused Triton Kernels.
Correctness tests for DSA Indexer K/S Buffer Access with Fused Triton Kernels.
This test verifies that the optimized Triton implementations (GetK, GetS, GetKAndS)
produce identical results to the torch_fast baseline implementations.
@@ -13,11 +13,11 @@ Test coverage:
import pytest
import torch
from sglang.srt.layers.attention.nsa.index_buf_accessor import GetK, GetKAndS, GetS
from sglang.srt.layers.attention.dsa.index_buf_accessor import GetK, GetKAndS, GetS
class MockNSATokenToKVPool:
"""Mock pool object that mimics NSATokenToKVPool for testing."""
class MockDSATokenToKVPool:
"""Mock pool object that mimics DSATokenToKVPool for testing."""
def __init__(
self,
@@ -78,7 +78,7 @@ class TestGetK:
seq_len = min(seq_len, max_seq_len)
# Create mock pool
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
@@ -119,7 +119,7 @@ class TestGetK:
num_pages = 10
seq_len = 320 # 5 pages
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -140,7 +140,7 @@ class TestGetK:
num_pages = 5
seq_len = 192 # 3 pages
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -171,7 +171,7 @@ class TestGetS:
seq_len = min(seq_len, max_seq_len)
# Create mock pool
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
@@ -212,7 +212,7 @@ class TestGetS:
num_pages = 10
seq_len = 320 # 5 pages
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -233,7 +233,7 @@ class TestGetS:
num_pages = 5
seq_len = 192 # 3 pages
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -267,7 +267,7 @@ class TestGetKAndS:
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
# Create mock pool
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
@@ -326,7 +326,7 @@ class TestGetKAndS:
seq_len = 320 # 5 pages
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -356,7 +356,7 @@ class TestGetKAndS:
seq_len = 192 # 3 pages
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -386,7 +386,7 @@ class TestGetKAndS:
seq_len = 100 # Not a multiple of 64
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -422,7 +422,7 @@ class TestEdgeCases:
seq_len = 1
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -455,7 +455,7 @@ class TestEdgeCases:
seq_len = 192 # Exactly 3 pages
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -488,7 +488,7 @@ class TestEdgeCases:
seq_len = 4096 # 64 pages
seq_len_tensor = torch.tensor([seq_len], dtype=torch.int64, device=device)
pool = MockNSATokenToKVPool(
pool = MockDSATokenToKVPool(
page_size=page_size, index_head_dim=index_head_dim, device=device
)
buf = create_test_buffer(num_pages, page_size, index_head_dim, device)
@@ -520,7 +520,7 @@ class TestEdgeCases:
def print_test_summary():
"""Print a summary message about the test suite."""
print("\n" + "=" * 80)
print("NSA Indexer K/S Buffer Accessor Correctness Tests")
print("DSA Indexer K/S Buffer Accessor Correctness Tests")
print("=" * 80)
print("Testing Triton implementations against torch_fast baseline:")
print(" - GetK.triton() vs GetK.torch_fast()")
test/manual/nightly/test_deepseek_v32_perf.py
+7 -7
View File
@@ -55,7 +55,7 @@ class TestNightlyDeepseekV32Performance(unittest.TestCase):
],
},
{
"name": "nsa",
"name": "dsa",
"other_args": [
"--trust-remote-code",
"--tp",
@@ -64,10 +64,10 @@ class TestNightlyDeepseekV32Performance(unittest.TestCase):
"8",
"--enable-dp-attention",
"--attention-backend",
"nsa",
"--nsa-prefill-backend",
"dsa",
"--dsa-prefill-backend",
"flashmla_sparse",
"--nsa-decode-backend",
"--dsa-decode-backend",
"flashmla_kv",
"--model-loader-extra-config",
'{"enable_multithread_load": true}',
@@ -80,10 +80,10 @@ class TestNightlyDeepseekV32Performance(unittest.TestCase):
"--tp",
"8",
"--attention-backend",
"nsa",
"--nsa-prefill-backend",
"dsa",
"--dsa-prefill-backend",
"flashmla_sparse",
"--nsa-decode-backend",
"--dsa-decode-backend",
"flashmla_kv",
"--model-loader-extra-config",
'{"enable_multithread_load": true}',
test/manual/test_dsa_alias_cli_registry_env.py
+302
View File
@@ -0,0 +1,302 @@
"""
Manual test for step 01: NSA → DSA user-facing alias layer.
Tests:
1. CLI: --dsa-* canonical flags write to dsa_* attrs
2. CLI: --nsa-* deprecated flags write to dsa_* attrs + log deprecation warning
3. Registry: "dsa" key creates the backend; "nsa" key triggers DeprecationWarning
4. Env: SGLANG_DSA_* canonical vars work
5. Env: SGLANG_NSA_* deprecated vars fall back to SGLANG_DSA_* with DeprecationWarning
Run:
python test/manual/test_dsa_alias_cli_registry_env.py
"""
import argparse
import os
import sys
import unittest
import warnings
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "../../python"))
class TestDSAChoicesAndFields(unittest.TestCase):
"""Verify DSA_CHOICES constant and ServerArgs field renaming."""
def setUp(self):
from sglang.srt.server_args import (
DSA_CHOICES,
DSA_PREFILL_CP_SPLIT_CHOICES,
NSA_CHOICES,
NSA_PREFILL_CP_SPLIT_CHOICES,
ServerArgs,
)
self.ServerArgs = ServerArgs
self.DSA_CHOICES = DSA_CHOICES
self.NSA_CHOICES = NSA_CHOICES
self.DSA_PREFILL_CP_SPLIT_CHOICES = DSA_PREFILL_CP_SPLIT_CHOICES
self.NSA_PREFILL_CP_SPLIT_CHOICES = NSA_PREFILL_CP_SPLIT_CHOICES
def test_dsa_choices_is_canonical(self):
self.assertIn("fa3", self.DSA_CHOICES)
self.assertIn("tilelang", self.DSA_CHOICES)
def test_nsa_choices_is_alias(self):
self.assertIs(
self.NSA_CHOICES,
self.DSA_CHOICES,
"NSA_CHOICES must be the same object as DSA_CHOICES",
)
def test_nsa_cp_split_choices_is_alias(self):
self.assertIs(
self.NSA_PREFILL_CP_SPLIT_CHOICES,
self.DSA_PREFILL_CP_SPLIT_CHOICES,
)
def test_serverargs_has_dsa_fields(self):
sa = self.ServerArgs
self.assertTrue(hasattr(sa, "dsa_prefill_backend"))
self.assertTrue(hasattr(sa, "dsa_decode_backend"))
self.assertTrue(hasattr(sa, "enable_dsa_prefill_context_parallel"))
self.assertTrue(hasattr(sa, "dsa_prefill_cp_mode"))
def test_serverargs_no_nsa_fields(self):
"""The nsa_* attributes should no longer exist on ServerArgs."""
sa = self.ServerArgs
self.assertFalse(
hasattr(sa, "nsa_prefill_backend"),
"nsa_prefill_backend should have been renamed",
)
self.assertFalse(
hasattr(sa, "nsa_decode_backend"),
"nsa_decode_backend should have been renamed",
)
self.assertFalse(hasattr(sa, "enable_nsa_prefill_context_parallel"))
self.assertFalse(hasattr(sa, "nsa_prefill_cp_mode"))
class TestCLICanonicalFlags(unittest.TestCase):
"""--dsa-* canonical flags write to dsa_* attributes with no warning."""
def setUp(self):
from sglang.srt.server_args import ServerArgs
self.parser = argparse.ArgumentParser()
ServerArgs.add_cli_args(self.parser)
def _parse(self, extra_args):
return self.parser.parse_args(["--model", "dummy"] + extra_args)
def test_dsa_prefill_backend_canonical(self):
args = self._parse(["--dsa-prefill-backend", "fa3"])
self.assertEqual(args.dsa_prefill_backend, "fa3")
def test_dsa_decode_backend_canonical(self):
args = self._parse(["--dsa-decode-backend", "tilelang"])
self.assertEqual(args.dsa_decode_backend, "tilelang")
def test_enable_dsa_prefill_cp_canonical(self):
args = self._parse(["--enable-dsa-prefill-context-parallel"])
self.assertTrue(args.enable_dsa_prefill_context_parallel)
def test_dsa_prefill_cp_mode_canonical(self):
args = self._parse(["--dsa-prefill-cp-mode", "in-seq-split"])
self.assertEqual(args.dsa_prefill_cp_mode, "in-seq-split")
def test_defaults_are_none_or_false(self):
args = self._parse([])
self.assertIsNone(args.dsa_prefill_backend)
self.assertIsNone(args.dsa_decode_backend)
self.assertFalse(args.enable_dsa_prefill_context_parallel)
self.assertEqual(args.dsa_prefill_cp_mode, "round-robin-split")
def test_attention_backend_dsa_key_in_choices(self):
args = self._parse(["--attention-backend", "dsa"])
self.assertEqual(args.attention_backend, "dsa")
class TestCLIDeprecatedFlags(unittest.TestCase):
"""--nsa-* deprecated flags write to dsa_* attributes and emit logger warning."""
def setUp(self):
import logging
from sglang.srt.server_args import ServerArgs
self.parser = argparse.ArgumentParser()
ServerArgs.add_cli_args(self.parser)
# Capture log output to detect deprecation warnings
self.log_records = []
handler = (
logging.handlers_collector(self.log_records)
if hasattr(logging, "handlers_collector")
else None
)
def _parse(self, extra_args):
return self.parser.parse_args(["--model", "dummy"] + extra_args)
def _parse_capture_warnings(self, extra_args):
"""Parse and capture both warnings.warn and logger output."""
import io
import logging
log_stream = io.StringIO()
handler = logging.StreamHandler(log_stream)
handler.setLevel(logging.WARNING)
root = logging.getLogger()
root.addHandler(handler)
try:
args = self._parse(extra_args)
finally:
root.removeHandler(handler)
return args, log_stream.getvalue()
def test_nsa_prefill_backend_deprecated_writes_to_dsa(self):
args, log_output = self._parse_capture_warnings(
["--nsa-prefill-backend", "fa3"]
)
self.assertEqual(args.dsa_prefill_backend, "fa3")
self.assertIn(
"deprecated",
log_output.lower(),
f"Expected deprecation warning in log; got: {log_output!r}",
)
def test_nsa_decode_backend_deprecated_writes_to_dsa(self):
args, log_output = self._parse_capture_warnings(
["--nsa-decode-backend", "tilelang"]
)
self.assertEqual(args.dsa_decode_backend, "tilelang")
self.assertIn("deprecated", log_output.lower())
def test_enable_nsa_prefill_cp_deprecated(self):
args, log_output = self._parse_capture_warnings(
["--enable-nsa-prefill-context-parallel"]
)
self.assertTrue(args.enable_dsa_prefill_context_parallel)
self.assertIn("deprecated", log_output.lower())
def test_nsa_prefill_cp_mode_deprecated(self):
args, log_output = self._parse_capture_warnings(
["--nsa-prefill-cp-mode", "in-seq-split"]
)
self.assertEqual(args.dsa_prefill_cp_mode, "in-seq-split")
self.assertIn("deprecated", log_output.lower())
def test_attention_backend_nsa_still_accepted(self):
"""attention_backend='nsa' still parses without error (registry handles the deprecation)."""
args = self._parse(["--attention-backend", "nsa"])
self.assertEqual(args.attention_backend, "nsa")
class TestAttentionRegistry(unittest.TestCase):
"""Registry: 'dsa' key creates backend; 'nsa' key emits DeprecationWarning."""
def test_dsa_key_registered(self):
from sglang.srt.layers.attention.attention_registry import ATTENTION_BACKENDS
self.assertIn("dsa", ATTENTION_BACKENDS)
def test_nsa_key_still_registered(self):
from sglang.srt.layers.attention.attention_registry import ATTENTION_BACKENDS
self.assertIn("nsa", ATTENTION_BACKENDS, "nsa must remain as deprecated alias")
def test_nsa_key_emits_deprecation_warning(self):
"""Calling the nsa factory should emit DeprecationWarning."""
from sglang.srt.layers.attention.attention_registry import ATTENTION_BACKENDS
nsa_factory = ATTENTION_BACKENDS.get("nsa")
self.assertIsNotNone(nsa_factory)
class _FakeRunner:
server_args = type("S", (), {"attention_backend": "nsa"})()
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
try:
nsa_factory(_FakeRunner())
except Exception:
pass # import errors OK; we only care about DeprecationWarning
dep_warns = [x for x in w if issubclass(x.category, DeprecationWarning)]
self.assertTrue(
len(dep_warns) > 0,
"Expected DeprecationWarning when using 'nsa' registry key",
)
self.assertIn("deprecated", str(dep_warns[0].message).lower())
class TestEnvVarAliases(unittest.TestCase):
"""SGLANG_DSA_* canonical; SGLANG_NSA_* fall back with DeprecationWarning."""
def setUp(self):
# Clean state for every test
for key in [
"SGLANG_DSA_FUSE_TOPK",
"SGLANG_NSA_FUSE_TOPK",
"SGLANG_DSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD",
"SGLANG_NSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD",
"SGLANG_DSA_ENABLE_MTP_PRECOMPUTE_METADATA",
"SGLANG_NSA_ENABLE_MTP_PRECOMPUTE_METADATA",
]:
os.environ.pop(key, None)
# Re-import to reset descriptor state
from importlib import reload
import sglang.srt.environ as e
reload(e)
from sglang.srt.environ import envs
self.envs = envs
def tearDown(self):
for key in [
"SGLANG_DSA_FUSE_TOPK",
"SGLANG_NSA_FUSE_TOPK",
"SGLANG_DSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD",
"SGLANG_NSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD",
]:
os.environ.pop(key, None)
def test_dsa_fuse_topk_default(self):
self.assertTrue(self.envs.SGLANG_DSA_FUSE_TOPK.get())
def test_dsa_fuse_topk_canonical_set(self):
os.environ["SGLANG_DSA_FUSE_TOPK"] = "0"
self.assertFalse(self.envs.SGLANG_DSA_FUSE_TOPK.get())
def test_nsa_fuse_topk_deprecated_fallback(self):
"""SGLANG_NSA_FUSE_TOPK=0 should be read by SGLANG_DSA_FUSE_TOPK with DeprecationWarning."""
os.environ["SGLANG_NSA_FUSE_TOPK"] = "0"
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
val = self.envs.SGLANG_DSA_FUSE_TOPK.get()
self.assertFalse(val)
dep = [x for x in w if issubclass(x.category, DeprecationWarning)]
self.assertTrue(
len(dep) > 0, "Expected DeprecationWarning for SGLANG_NSA_FUSE_TOPK"
)
def test_dsa_threshold_default(self):
self.assertEqual(
self.envs.SGLANG_DSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD.get(), 2048
)
def test_nsa_threshold_deprecated_fallback(self):
os.environ["SGLANG_NSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD"] = "1024"
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
val = self.envs.SGLANG_DSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD.get()
self.assertEqual(val, 1024)
dep = [x for x in w if issubclass(x.category, DeprecationWarning)]
self.assertTrue(len(dep) > 0)
if __name__ == "__main__":
unittest.main(verbosity=2)
test/registered/8-gpu-models/test_deepseek_v32.py
+19 -19
View File
@@ -102,55 +102,55 @@ class TestDeepseekV32(unittest.TestCase):
)
@unittest.skipIf(is_blackwell_system(), "Requires H200 system")
def test_deepseek_v32_nsa_backends(self):
"""Test NSA attention backend variants (H200 only).
def test_deepseek_v32_dsa_backends(self):
"""Test DSA attention backend variants (H200 only).
Tests three NSA backend configurations:
Tests three DSA backend configurations:
- flashmla: flashmla_sparse prefill + flashmla_kv decode
- fa3: FA3 prefill + FA3 decode
- fp8kvcache: default backends with FP8 KV cache
"""
NSA_FLASHMLA_ARGS = [
"--attention-backend=nsa",
"--nsa-prefill-backend=flashmla_sparse",
"--nsa-decode-backend=flashmla_kv",
DSA_FLASHMLA_ARGS = [
"--attention-backend=dsa",
"--dsa-prefill-backend=flashmla_sparse",
"--dsa-decode-backend=flashmla_kv",
]
NSA_FA3_ARGS = [
"--attention-backend=nsa",
"--nsa-prefill-backend=fa3",
"--nsa-decode-backend=fa3",
DSA_FA3_ARGS = [
"--attention-backend=dsa",
"--dsa-prefill-backend=fa3",
"--dsa-decode-backend=fa3",
]
NSA_FP8KV_ARGS = [
"--attention-backend=nsa",
DSA_FP8KV_ARGS = [
"--attention-backend=dsa",
"--kv-cache-dtype=fp8_e4m3",
]
nsa_variants = [
dsa_variants = [
# flashmla backend
ModelLaunchSettings(
DEEPSEEK_V32_MODEL_PATH,
tp_size=8,
extra_args=BASE_ARGS + DP_ARGS + NSA_FLASHMLA_ARGS,
extra_args=BASE_ARGS + DP_ARGS + DSA_FLASHMLA_ARGS,
),
# fa3 backend
ModelLaunchSettings(
DEEPSEEK_V32_MODEL_PATH,
tp_size=8,
extra_args=BASE_ARGS + DP_ARGS + NSA_FA3_ARGS,
extra_args=BASE_ARGS + DP_ARGS + DSA_FA3_ARGS,
),
# fp8 kv cache
ModelLaunchSettings(
DEEPSEEK_V32_MODEL_PATH,
tp_size=8,
extra_args=BASE_ARGS + DP_ARGS + NSA_FP8KV_ARGS,
extra_args=BASE_ARGS + DP_ARGS + DSA_FP8KV_ARGS,
),
]
run_combined_tests(
models=nsa_variants,
test_name="DeepSeek-V3.2 NSA Backends",
models=dsa_variants,
test_name="DeepSeek-V3.2 DSA Backends",
accuracy_params=AccuracyTestParams(
dataset="gsm8k", baseline_accuracy=GSM8K_BASELINE
),
test/registered/8-gpu-models/test_dsa_models_hisparse.py
+1 -1
View File
@@ -38,7 +38,7 @@ class TestGLM5DPHiSparse(CustomTestCase):
"--disable-radix-cache",
"--kv-cache-dtype",
"bfloat16",
"--nsa-decode-backend",
"--dsa-decode-backend",
"flashmla_sparse",
"--enable-hisparse",
"--hisparse-config",
test/registered/8-gpu-models/test_return_indexer_topk.py
+1 -1
View File
@@ -33,7 +33,7 @@ logger = logging.getLogger(__name__)
class TestReturnIndexerTopk(CustomTestCase):
"""Indexer-topk capture e2e test for DSv3.2 (NSA).
"""Indexer-topk capture e2e test for DSv3.2 (DSA).
Single server with `--enable-return-indexer-topk` and `index_topk_freq=2`.
Validates the native `/generate` endpoint only — OpenAI-protocol surface
test/registered/amd/accuracy/mi30x/test_glm51_eval_amd.py
+4 -4
View File
@@ -1,6 +1,6 @@
"""AMD GLM-5.1 GSM8K Completion Evaluation Test (8-GPU)
Tests GLM-5.1-FP8 with NSA attention backend using few-shot
Tests GLM-5.1-FP8 with DSA attention backend using few-shot
completion benchmark on MI325/MI300X.
Registry: nightly-amd-accuracy-8-gpu-glm51 suite
@@ -58,16 +58,16 @@ GLM51_MODELS = [
tp_size=8,
accuracy_threshold=0.93,
timeout=3600,
variant="nsa",
variant="dsa",
other_args=[
"--trust-remote-code",
"--reasoning-parser",
"glm45",
"--tool-call-parser",
"glm47",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--chunked-prefill-size",
"131072",
test/registered/amd/accuracy/mi30x/test_glm5_eval_amd.py
+6 -6
View File
@@ -1,6 +1,6 @@
"""AMD GLM-5 GSM8K Completion Evaluation Test (8-GPU)
Tests GLM-5 with NSA attention backend using few-shot completion
Tests GLM-5 with DSA attention backend using few-shot completion
benchmark on MI325/MI300X.
Registry: nightly-amd-accuracy-8-gpu-glm5 suite
@@ -55,24 +55,24 @@ class ModelConfig:
return self.model_path
# GLM-5 models for MI325/MI300X - NSA attention backend
# GLM-5 models for MI325/MI300X - DSA attention backend
GLM5_MODELS = [
# GLM-5 with NSA attention (TP=8)
# GLM-5 with DSA attention (TP=8)
ModelConfig(
model_path="zai-org/GLM-5-FP8",
tp_size=8,
accuracy_threshold=0.93,
timeout=3600,
variant="nsa",
variant="dsa",
other_args=[
"--trust-remote-code",
"--reasoning-parser",
"glm45",
"--tool-call-parser",
"glm47",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--chunked-prefill-size",
"131072",
test/registered/amd/accuracy/mi35x/test_deepseek_v32_dp_eval_mi35x.py
+2 -2
View File
@@ -60,9 +60,9 @@ class TestDeepseekV32DP(CustomTestCase):
"--enable-dp-attention",
"--model-loader-extra-config",
'{"enable_multithread_load": true}',
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
]
cls.process = popen_launch_server(
test/registered/amd/accuracy/mi35x/test_deepseek_v32_eval_mi35x.py
+2 -2
View File
@@ -78,9 +78,9 @@ MI35X_DEEPSEEK_V32_MODELS = [
variant="basic",
other_args=[
"--trust-remote-code",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--mem-fraction-static",
"0.85",
test/registered/amd/accuracy/mi35x/test_deepseek_v32_mtp_eval_mi35x.py
+2 -2
View File
@@ -59,9 +59,9 @@ class TestDeepseekV32TPMTP(CustomTestCase):
"--trust-remote-code",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--speculative-algorithm",
"EAGLE",
test/registered/amd/accuracy/mi35x/test_glm51_eval_mi35x.py
+4 -4
View File
@@ -1,6 +1,6 @@
"""MI35x GLM-5.1 GSM8K Completion Evaluation Test (8-GPU)
Tests GLM-5.1-FP8 with NSA attention backend using few-shot
Tests GLM-5.1-FP8 with DSA attention backend using few-shot
completion benchmark on MI35x.
Registry: nightly-amd-8-gpu-mi35x-glm51 suite
@@ -62,16 +62,16 @@ MI35X_GLM51_MODELS = [
tp_size=8,
accuracy_threshold=0.93,
timeout=5400,
variant="nsa",
variant="dsa",
other_args=[
"--trust-remote-code",
"--reasoning-parser",
"glm45",
"--tool-call-parser",
"glm47",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--chunked-prefill-size",
"131072",
test/registered/amd/accuracy/mi35x/test_glm5_eval_mi35x.py
+6 -6
View File
@@ -1,6 +1,6 @@
"""MI35x GLM-5 GSM8K Completion Evaluation Test (8-GPU)
Tests GLM-5 with NSA attention backend using few-shot completion
Tests GLM-5 with DSA attention backend using few-shot completion
benchmark on MI35x.
Registry: nightly-amd-8-gpu-mi35x-glm5 suite
@@ -60,24 +60,24 @@ class ModelConfig:
return self.model_path
# GLM-5 models for MI35x - NSA attention backend
# GLM-5 models for MI35x - DSA attention backend
MI35X_GLM5_MODELS = [
# GLM-5 with NSA attention (TP=8)
# GLM-5 with DSA attention (TP=8)
ModelConfig(
model_path="zai-org/GLM-5-FP8",
tp_size=8,
accuracy_threshold=0.93,
timeout=5400,
variant="nsa",
variant="dsa",
other_args=[
"--trust-remote-code",
"--reasoning-parser",
"glm45",
"--tool-call-parser",
"glm47",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--chunked-prefill-size",
"131072",
test/registered/amd/perf/mi30x/test_glm51_perf_amd.py
+4 -4
View File
@@ -1,6 +1,6 @@
"""Nightly performance benchmark for GLM-5.1 on MI30x.
Tests GLM-5.1-FP8 with NSA attention backend using bench_one_batch
Tests GLM-5.1-FP8 with DSA attention backend using bench_one_batch
on 8 GPUs with TP=8, FP8 KV cache.
Model path can be configured via GLM51_MODEL_PATH environment variable.
@@ -53,7 +53,7 @@ PROFILE_DIR = "performance_profiles_glm51"
class TestNightlyGLM51Performance(unittest.TestCase):
"""Nightly performance benchmark for GLM-5.1 on MI30x.
Tests GLM-5.1-FP8 with NSA attention backend on TP=8.
Tests GLM-5.1-FP8 with DSA attention backend on TP=8.
"""
@classmethod
@@ -74,9 +74,9 @@ class TestNightlyGLM51Performance(unittest.TestCase):
"glm47",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--kv-cache-dtype",
"fp8_e4m3",
test/registered/amd/perf/mi30x/test_glm5_perf_amd.py
+4 -4
View File
@@ -1,6 +1,6 @@
"""Nightly performance benchmark for GLM-5 on MI30x.
Tests GLM-5 with NSA attention backend using bench_one_batch on 8 GPUs.
Tests GLM-5 with DSA attention backend using bench_one_batch on 8 GPUs.
Model paths can be configured via environment variables:
- GLM5_MODEL_PATH: Path to GLM-5 model (default: zai-org/GLM-5-FP8)
@@ -54,7 +54,7 @@ PROFILE_DIR = "performance_profiles_glm5"
class TestNightlyGLM5Performance(unittest.TestCase):
"""Nightly performance benchmark for GLM-5.
Tests GLM-5 with NSA attention backend on TP=8.
Tests GLM-5 with DSA attention backend on TP=8.
"""
@classmethod
@@ -75,9 +75,9 @@ class TestNightlyGLM5Performance(unittest.TestCase):
"glm47",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--kv-cache-dtype",
"fp8_e4m3",
test/registered/amd/perf/mi35x/test_deepseek_v32_basic_perf_mi35x.py
+3 -3
View File
@@ -78,16 +78,16 @@ class TestNightlyDeepseekV32BasicPerformance(unittest.TestCase):
cls.output_lens = tuple(_parse_int_list_env("NIGHTLY_OUTPUT_LENS", "512"))
# Basic variant configuration for DeepSeek-V3.2
# MI35x uses tilelang NSA backends
# MI35x uses tilelang DSA backends
cls.variant_config = {
"name": "basic",
"other_args": [
"--trust-remote-code",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--mem-fraction-static",
"0.85",
test/registered/amd/perf/mi35x/test_deepseek_v32_mtp_perf_mi35x.py
+3 -3
View File
@@ -132,16 +132,16 @@ class TestNightlyDeepseekV32MTPPerformance(unittest.TestCase):
cls.output_lens = tuple(_parse_int_list_env("NIGHTLY_OUTPUT_LENS", "512"))
# MTP variant configuration for DeepSeek-V3.2
# MI35x uses tilelang NSA backends + EAGLE speculative decoding
# MI35x uses tilelang DSA backends + EAGLE speculative decoding
cls.variant_config = {
"name": "mtp",
"other_args": [
"--trust-remote-code",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--speculative-algorithm",
"EAGLE",
test/registered/amd/perf/mi35x/test_glm51_perf_mi35x.py
+4 -4
View File
@@ -1,6 +1,6 @@
"""MI35x Nightly performance benchmark for GLM-5.1.
Tests GLM-5.1-FP8 with NSA attention backend using bench_one_batch
Tests GLM-5.1-FP8 with DSA attention backend using bench_one_batch
on 8 GPUs with TP=8, FP8 KV cache.
Registry: nightly-perf-8-gpu-mi35x-glm51 suite
@@ -55,7 +55,7 @@ PROFILE_DIR = "performance_profiles_glm51_mi35x"
class TestGLM51PerfMI35x(unittest.TestCase):
"""Nightly performance benchmark for GLM-5.1 on MI35x.
Tests GLM-5.1-FP8 with NSA attention backend on TP=8.
Tests GLM-5.1-FP8 with DSA attention backend on TP=8.
"""
@classmethod
@@ -76,9 +76,9 @@ class TestGLM51PerfMI35x(unittest.TestCase):
"glm47",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--kv-cache-dtype",
"fp8_e4m3",
test/registered/amd/perf/mi35x/test_glm5_perf_mi35x.py
+4 -4
View File
@@ -1,6 +1,6 @@
"""MI35x Nightly performance benchmark for GLM-5.
Tests GLM-5 with NSA attention backend using bench_one_batch on 8 GPUs.
Tests GLM-5 with DSA attention backend using bench_one_batch on 8 GPUs.
Registry: nightly-perf-8-gpu-mi35x-glm5 suite
"""
@@ -54,7 +54,7 @@ PROFILE_DIR = "performance_profiles_glm5_mi35x"
class TestGLM5PerfMI35x(unittest.TestCase):
"""Nightly performance benchmark for GLM-5 on MI35x.
Tests GLM-5 with NSA attention backend on TP=8.
Tests GLM-5 with DSA attention backend on TP=8.
"""
@classmethod
@@ -75,9 +75,9 @@ class TestGLM5PerfMI35x(unittest.TestCase):
"glm47",
"--tp",
"8",
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
"--kv-cache-dtype",
"fp8_e4m3",
test/registered/amd/test_deepseek_v32_basic.py
+4 -4
View File
@@ -38,9 +38,9 @@ class TestDeepseekV32DP(CustomTestCase):
]
if is_in_amd_ci():
other_args += [
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
]
@@ -106,9 +106,9 @@ class TestDeepseekV32TP(CustomTestCase):
]
if is_in_amd_ci():
other_args += [
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
]
test/registered/amd/test_deepseek_v32_mtp.py
+4 -4
View File
@@ -54,9 +54,9 @@ class TestDeepseekV32DPMTP(CustomTestCase):
]
if is_in_amd_ci():
other_args += [
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
]
cls.process = popen_launch_server(
@@ -146,9 +146,9 @@ class TestDeepseekV32TPMTP(CustomTestCase):
]
if is_in_amd_ci():
other_args += [
"--nsa-prefill-backend",
"--dsa-prefill-backend",
"tilelang",
"--nsa-decode-backend",
"--dsa-decode-backend",
"tilelang",
]
cls.process = popen_launch_server(
test/registered/cp/test_deepseek_v32_cp_single_node.py
+4 -4
View File
@@ -31,8 +31,8 @@ class TestDeepseekV32CPInSeqSplit(CustomTestCase):
"2",
"--attn-cp-size",
"4",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"in-seq-split",
"--speculative-algorithm",
"EAGLE",
@@ -97,8 +97,8 @@ class TestDeepseekV32CPRoundRobinSplit(CustomTestCase):
"8",
"--attn-cp-size",
"8",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--speculative-algorithm",
"EAGLE",
test/registered/dsv4/test_deepseek_v4_flash_fp4_b200.py
+2 -2
View File
@@ -158,8 +158,8 @@ class TestDSV4FlashFP4B200Balanced_CP(ServerSanityMixin, CustomTestCase):
"1",
"--speculative-num-draft-tokens",
"2",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"--enable-dsa-prefill-context-parallel",
"--dsa-prefill-cp-mode",
"round-robin-split",
"--deepep-config",
DEEPEP_CONFIG,
test/registered/kernels/test_nsa_indexer.py → test/registered/kernels/test_dsa_indexer.py
+22 -22
View File
@@ -11,15 +11,15 @@ from sglang.test.ci.ci_register import register_cuda_ci
_dp_attn.get_attention_tp_size = lambda: 1 # TP size = 1 for unit test
from sglang.srt.configs.model_config import AttentionArch
from sglang.srt.layers.attention.nsa.nsa_indexer import (
from sglang.srt.layers.attention.dsa.dsa_indexer import (
BaseIndexerMetadata,
Indexer,
rotate_activation,
)
from sglang.srt.layers.attention.nsa_backend import NativeSparseAttnBackend
from sglang.srt.layers.attention.dsa_backend import DeepseekSparseAttnBackend
from sglang.srt.layers.layernorm import LayerNorm
from sglang.srt.layers.linear import LinearBase
from sglang.srt.mem_cache.memory_pool import NSATokenToKVPool
from sglang.srt.mem_cache.memory_pool import DSATokenToKVPool
from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
from sglang.srt.server_args import ServerArgs, set_global_server_args_for_scheduler
from sglang.test.test_utils import CustomTestCase
@@ -136,7 +136,7 @@ class MockIndexerMetadata(BaseIndexerMetadata):
"""Return: seq lens for each batch."""
return torch.tensor(self.seq_lens, dtype=torch.int32, device=self.device)
def get_nsa_extend_len_cpu(self) -> List[int]:
def get_dsa_extend_len_cpu(self) -> List[int]:
"""
Return: extend seq lens for each batch.
"""
@@ -179,7 +179,7 @@ class MockModelRunner:
max_context_len = self.config["context_len"]
max_batch_size = self.config["max_bs"]
# Create mock hf_config for NSA - instantiate it as an object, not a type
# Create mock hf_config for DSA - instantiate it as an object, not a type
hf_config = type(
"HfConfig",
(),
@@ -224,9 +224,9 @@ class MockModelRunner:
},
)()
# Create NSATokenToKVPool
# Create DSATokenToKVPool
max_total_num_tokens = max_batch_size * max_context_len
self.token_to_kv_pool = NSATokenToKVPool(
self.token_to_kv_pool = DSATokenToKVPool(
size=max_total_num_tokens,
page_size=self.config["page_size"],
dtype=self.config["kv_cache_dtype"],
@@ -239,7 +239,7 @@ class MockModelRunner:
kv_cache_dim=self.config["kv_lora_rank"] + self.config["qk_rope_head_dim"],
)
# Required by backend with NSA-specific attributes
# Required by backend with DSA-specific attributes
self.server_args = type(
"ServerArgs",
(),
@@ -248,21 +248,21 @@ class MockModelRunner:
"speculative_eagle_topk": None,
"speculative_num_draft_tokens": 0,
"enable_deterministic_inference": False,
"nsa_prefill_backend": "flashmla_sparse",
"nsa_decode_backend": "fa3",
"dsa_prefill_backend": "flashmla_sparse",
"dsa_decode_backend": "fa3",
},
)()
@unittest.skipIf(not torch.cuda.is_available(), "Test requires CUDA")
class TestNSAIndexer(CustomTestCase):
class TestDSAIndexer(CustomTestCase):
@classmethod
def setUpClass(cls):
"""Set up global server args for testing."""
server_args = ServerArgs(model_path="dummy")
server_args.enable_dp_attention = False
server_args.nsa_prefill_backend = "flashmla_sparse"
server_args.nsa_decode_backend = "flashmla_sparse"
server_args.dsa_prefill_backend = "flashmla_sparse"
server_args.dsa_decode_backend = "flashmla_sparse"
set_global_server_args_for_scheduler(server_args)
# Check GPU capability for FP8
@@ -289,7 +289,7 @@ class TestNSAIndexer(CustomTestCase):
if config_override:
config.update(config_override)
self.model_runner = MockModelRunner(config)
self.backend = NativeSparseAttnBackend(self.model_runner)
self.backend = DeepseekSparseAttnBackend(self.model_runner)
def _create_indexer(self, **kwargs):
"""Create an Indexer instance with default parameters."""
@@ -417,7 +417,7 @@ class TestNSAIndexer(CustomTestCase):
"Output should have padding or exact topk size",
)
@patch("sglang.srt.layers.attention.nsa.nsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.dsa.dsa_indexer.deep_gemm")
def test_indexer_basic_creation(self, mock_deep_gemm):
"""Test basic indexer creation and initialization."""
mock_deep_gemm.get_num_sms.return_value = 132
@@ -431,8 +431,8 @@ class TestNSAIndexer(CustomTestCase):
self.assertEqual(indexer.index_topk, self.config["index_topk"])
self.assertEqual(indexer.layer_id, self.config["layer_id"])
@patch("sglang.srt.layers.attention.nsa.nsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.nsa.triton_kernel.act_quant")
@patch("sglang.srt.layers.attention.dsa.dsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.dsa.triton_kernel.act_quant")
def test_forward_extend_mode(self, mock_act_quant, mock_deep_gemm):
"""Test indexer forward pass in extend mode."""
if not self.supports_fp8:
@@ -513,8 +513,8 @@ class TestNSAIndexer(CustomTestCase):
topk_indices, self.batch_size, self.seq_len, self.config["index_topk"]
)
@patch("sglang.srt.layers.attention.nsa.nsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.nsa.triton_kernel.act_quant")
@patch("sglang.srt.layers.attention.dsa.dsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.dsa.triton_kernel.act_quant")
def test_forward_decode_mode(self, mock_act_quant, mock_deep_gemm):
"""Test indexer forward pass in decode mode."""
if not self.supports_fp8:
@@ -627,7 +627,7 @@ class TestNSAIndexer(CustomTestCase):
self.assertEqual(topk_indices.shape, (batch_size, topk))
# TODO: enable this test after indexer accuracy aligned
# @patch("sglang.srt.layers.attention.nsa.nsa_indexer.deep_gemm")
# @patch("sglang.srt.layers.attention.dsa.dsa_indexer.deep_gemm")
# def test_indexer_with_different_topk(self, mock_deep_gemm):
# """Test indexer with different topk values."""
# mock_deep_gemm.get_num_sms.return_value = 132
@@ -637,7 +637,7 @@ class TestNSAIndexer(CustomTestCase):
# indexer = self._create_indexer(index_topk=topk)
# self.assertEqual(indexer.index_topk, topk)
@patch("sglang.srt.layers.attention.nsa.nsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.dsa.dsa_indexer.deep_gemm")
def test_indexer_with_fused_wk(self, mock_deep_gemm):
"""Test indexer creation with fused wk and weights projection."""
mock_deep_gemm.get_num_sms.return_value = 132
@@ -647,7 +647,7 @@ class TestNSAIndexer(CustomTestCase):
indexer = self._create_indexer()
self.assertIsNotNone(indexer)
@patch("sglang.srt.layers.attention.nsa.nsa_indexer.deep_gemm")
@patch("sglang.srt.layers.attention.dsa.dsa_indexer.deep_gemm")
def test_indexer_with_alt_stream(self, mock_deep_gemm):
"""Test indexer creation with alternative CUDA stream."""
mock_deep_gemm.get_num_sms.return_value = 132
test/registered/quant/test_deepseek_v32_fp4_mtp_4gpu.py
+2 -2
View File
@@ -37,7 +37,7 @@ class TestDeepseekV32FP4DPSpecV2(CustomTestCase):
"4",
"--enable-dp-attention",
"--attention-backend",
"nsa",
"dsa",
"--moe-runner-backend",
"flashinfer_trtllm",
"--quantization",
@@ -127,7 +127,7 @@ class TestDeepseekV32FP4TPSpecV2(CustomTestCase):
"--tp",
"4",
"--attention-backend",
"nsa",
"dsa",
"--moe-runner-backend",
"flashinfer_trtllm",
"--quantization",
test/registered/unit/managers/test_hisparse_unit.py
+2 -2
View File
@@ -94,11 +94,11 @@ class TestHiSparseUnit(unittest.TestCase):
global_page_size = 1 if is_hip() else PAGE_SIZE
from sglang.srt.mem_cache.hisparse_memory_pool import (
HiSparseNSATokenToKVPool,
HiSparseDSATokenToKVPool,
HiSparseTokenToKVPoolAllocator,
)
cls.device_pool = HiSparseNSATokenToKVPool(
cls.device_pool = HiSparseDSATokenToKVPool(
size=SIZE,
page_size=global_page_size,
kv_lora_rank=KV_LORA_RANK,
test/registered/unit/mem_cache/test_nsa_pool_host_unit.py → test/registered/unit/mem_cache/test_dsa_pool_host_unit.py
+7 -7
View File
@@ -2,11 +2,11 @@ import unittest
import torch
from sglang.srt.mem_cache.memory_pool import NSATokenToKVPool
from sglang.srt.mem_cache.memory_pool import DSATokenToKVPool
from sglang.srt.mem_cache.memory_pool_host import (
ALLOC_MEMORY_FUNCS,
DSAIndexerPoolHost,
MLATokenToKVPoolHost,
NSAIndexerPoolHost,
alloc_with_pin_memory,
)
from sglang.srt.utils import is_cuda, is_hip, is_npu, is_xpu
@@ -15,12 +15,12 @@ from sglang.test.ci.ci_register import register_cuda_ci
register_cuda_ci(est_time=9, stage="base-b", runner_config="1-gpu-small")
class TestNSAHiCacheTransfer(unittest.TestCase):
class TestDSAHiCacheTransfer(unittest.TestCase):
def setUp(self):
if not torch.cuda.is_available():
self.skipTest("CUDA is required for NSA host transfer tests.")
self.skipTest("CUDA is required for DSA host transfer tests.")
if is_npu() or is_xpu():
self.skipTest("NSA host transfer tests only support CUDA/ROCm.")
self.skipTest("DSA host transfer tests only support CUDA/ROCm.")
if not (is_cuda() or is_hip()):
self.skipTest("CUDA/ROCm not available.")
@@ -42,7 +42,7 @@ class TestNSAHiCacheTransfer(unittest.TestCase):
layer_num = 2
size = page_size * 4
device_pool = NSATokenToKVPool(
device_pool = DSATokenToKVPool(
size=size,
page_size=page_size,
kv_lora_rank=128,
@@ -70,7 +70,7 @@ class TestNSAHiCacheTransfer(unittest.TestCase):
allocator_type="default",
override_kv_cache_dim=device_pool.kv_cache_dim,
)
indexer_host = NSAIndexerPoolHost(
indexer_host = DSAIndexerPoolHost(
device_pool=device_pool,
anchor_host=mla_host,
layout="layer_first",
test/registered/unit/platforms/test_platform_interface.py
+1 -1
View File
@@ -71,7 +71,7 @@ class _StubPlatform(SRTPlatform):
def get_mla_kv_pool_cls(self):
return object
def get_nsa_kv_pool_cls(self):
def get_dsa_kv_pool_cls(self):
return object
def get_paged_allocator_cls(self):