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

[CI] Lower GLM-5.2 NVFP4 MTP speed threshold (#31289)

Browse Source
This commit is contained in:
Mohammad Miadh Angkad
2026-07-15 00:39:58 -07:00
committed by GitHub
parent fbcbe0a986
commit 5af670284e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/models_e2e/test_dsa_glm52_nvfp4_tp_mtp.py
+1 -1
View File
@@ -21,7 +21,7 @@ class TestGLM52NVFP4TPMTP(
model = "nvidia/GLM-5.2-NVFP4" model = "nvidia/GLM-5.2-NVFP4"
tp_size = 4 tp_size = 4
mem_fraction_static = 0.8 mem_fraction_static = 0.8
bs_1_speed_thres = 300 bs_1_speed_thres = 250
extra_server_args = [ extra_server_args = [
"--moe-runner-backend", "--moe-runner-backend",
"flashinfer_trtllm", "flashinfer_trtllm",