minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 14 Packages Projects Releases Wiki Activity

[DeepSeekV3.2] Enable pure TP & Partial DP Attention (#13646)

Browse Source
This commit is contained in:
YAMY
2025-11-30 15:59:23 -08:00
committed by GitHub
parent c72f0756d2
commit decb48965d
7 changed files with 286 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/manual/nightly/test_deepseek_v32_perf.py
+25
View File
@@ -25,6 +25,9 @@ class TestNightlyDeepseekV32Performance(unittest.TestCase):
"--trust-remote-code",
"--tp",
"8",
"--dp",
"8",
"--enable-dp-attention",
"--model-loader-extra-config",
'{"enable_multithread_load": true}',
],
@@ -35,6 +38,9 @@ class TestNightlyDeepseekV32Performance(unittest.TestCase):
"--trust-remote-code",
"--tp",
"8",
"--dp",
"8",
"--enable-dp-attention",
"--speculative-algorithm",
"EAGLE",
"--speculative-num-steps",
@@ -51,6 +57,25 @@ class TestNightlyDeepseekV32Performance(unittest.TestCase):
},
{
"name": "nsa",
"other_args": [
"--trust-remote-code",
"--tp",
"8",
"--dp",
"8",
"--enable-dp-attention",
"--attention-backend",
"nsa",
"--nsa-prefill-backend",
"flashmla_sparse",
"--nsa-decode-backend",
"flashmla_kv",
"--model-loader-extra-config",
'{"enable_multithread_load": true}',
],
},
{
"name": "pure_tp",
"other_args": [
"--trust-remote-code",
"--tp",