iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Quantization] Support packed NVFP4 Qwen4Exp PLE embeddings (#56273)

Browse Source 
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Kartikey Vyas <kartikey@artificialanalysis.ai>
This commit is contained in:
Stefano Castagnetta
2026-10-14 08:24:55 +08:00
committed by GitHub
co-authored by Kartikey Vyas
parent 87e7dce3a7
commit 4e0681ed56
6 changed files with 443 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test_areas/models_basic.yaml
+1 -1
View File
@@ -212,7 +212,7 @@ steps:
- tests/models/qwen4_exp/
commands:
- pytest -v -s models/qwen4_exp/test_hc_ops.py models/qwen4_exp/test_qsa_prepare.py models/qwen4_exp/test_qsa_reference.py
- pytest -v -s models/qwen4_exp/test_ple.py -k test_fused_conv_correctness
- pytest -v -s models/qwen4_exp/test_ple.py
mirror:
amd:
label: ":amd: (MI355 DPX) Qwen4 Exp"