COMMITS
/ backends/qualcomm/qnn_preprocess.py May 1, 2025
H
Qualcomm AI Engine Direct - Support Qnn IR backend in online preparation
haowhsu-quic committed
April 2, 2025
S
Qualcomm AI Engine Direct - Add QNN support for to_edge_transform_and_lower (#9643)
shewu-quic committed
February 14, 2025
H
Qualcomm AI Engine Direct - XR model enablement pipe_clean (#8299)
haowhsu-quic committed
November 18, 2024
H
Dev weight sharing
haowhsu-quic committed
October 16, 2024
W
Qualcomm AI Engine Direct - Observer Fix and remove unused passes (#6225)
winskuo-quic committed
October 9, 2024
T
Move qualcomm.passes to qualcomm._passes (#5920)
Tarun Karuturi committed
July 17, 2024
H
Qualcomm AI Engine Direct - enable loading context binary directly (#4163)
haowhsu-quic committed
July 6, 2024
S
Qualcomm AI Engine Direct - Support kv_cached stories 110M llama2 (#4142)
shewu-quic committed
May 31, 2024
W
Qualcomm AI Engine Direct - gMLP Enablement (#3774)
winskuo-quic committed
April 7, 2024
W
Qualcomm AI Engine Direct - Requantization Mechanism Implementation (#2823)
winskuo-quic committed
March 22, 2024
March 5, 2024
S
Qualcomm AI Engine Direct - enable per-tensor dump mechanism (#1294)
shewu-quic committed
March 3, 2024
H
Qualcomm AI Engine Direct - support embedding op (#2057)
haowhsu-quic committed
February 22, 2024
J
Qualcomm AI Engine Direct - LLAMA2 Infrastructure (#2020)
Joey Tsai committed
February 9, 2024
W
Qualcomm AI Engine Direct - Enable W2l (#1767)
winskuo-quic committed
February 2, 2024
A
Remove calls to torch._export (#1804)
Angela Yi committed
November 27, 2023
S
Enable mobilebert quant example (#1043)
shewu-quic committed
November 9, 2023
H
Qualcomm AI Engine Direct - retire "_unlift" IR capture option (#1130)
haowhsu-quic committed
October 5, 2023
H
Qualcomm AI Engine Direct Backend (#490)
Hao-Wei Hsu committed