onnxruntime
[MLAS] DequantizeLinear int8/uint8
#24818
Merged

[MLAS] DequantizeLinear int8/uint8 #24818

adrianlizarraga merged 11 commits into main from adrianl/dequantize-mlas
adrianlizarraga
adrianlizarraga sse2 dequantize linear
55384718
adrianlizarraga Merge branch 'main' into adrianl/dequantize-mlas
19157200
adrianlizarraga DQ NEON intrinsics
108ca0d9
adrianlizarraga Merge branch 'main' into adrianl/dequantize-mlas
8f190f0b
adrianlizarraga Rework SSE 2 to use a loop that loads 16 inputs at a time
b71efa07
adrianlizarraga adrianlizarraga changed the title [MLAS] DequantizeLinear int8/uint8 [MLAS] DequantizeLinear int8/uint8 (multithreaded and vectorized) 249 days ago
adrianlizarraga adrianlizarraga changed the title [MLAS] DequantizeLinear int8/uint8 (multithreaded and vectorized) [MLAS] DequantizeLinear int8/uint8 249 days ago
adrianlizarraga Disable new dequantize unit test for webgpu because webgpu requires t…
a288bcb1
adrianlizarraga adrianlizarraga requested a review from edgchen1 edgchen1 242 days ago
adrianlizarraga adrianlizarraga marked this pull request as ready for review 242 days ago
hariharans29
adrianlizarraga Merge branch 'main' into adrianl/dequantize-mlas
73101067
adrianlizarraga Only enable multithreaded DQ for client/on-device workloads
f590ab0b
adrianlizarraga Mark thread_pool as unused
99e21927
adrianlizarraga typo fix
a547ee91
adrianlizarraga
adrianlizarraga commented on 2025-07-09
adrianlizarraga Update onnxruntime/core/providers/cpu/quantization/quantize_linear.cc
cda95458
jywu-msft
jywu-msft commented on 2025-07-09
jywu-msft
jywu-msft approved these changes on 2025-07-09
adrianlizarraga adrianlizarraga merged b49fc62e into main 199 days ago
adrianlizarraga adrianlizarraga deleted the adrianl/dequantize-mlas branch 199 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone