COMMITS
/ backends/qualcomm/quantizer/custom_annotation.py April 15, 2025
W
Qualcomm AI Engine Direct - Mimi Enablement Stage 2 (#10098)
winskuo-quic committed
January 29, 2025
January 23, 2025
C
K
[ExecuTorch][BE] Split kv cache and SDPA for better code sharing
Kimish Patel committed
January 18, 2025
W
Qualcomm AI Engine Direct - Unify Llama2&Llama3 and Small Accuracy Improvement. (#7618)
winskuo-quic committed
January 8, 2025
S
Qualcomm AI Engine Direct - Optimize static llama phase 2
shewu-quic committed
December 3, 2024
C
Qualcomm AI Engine Direct - Suport batch prefill mode for llama3.2 (#6983)
Chun-I Tsai committed
November 22, 2024
S
November 20, 2024
C
Fix custom annotation (#6978)
cccclai committed
S
Qualcomm AI Engine Direct - Optimization in static llama
shewu-quic committed
November 18, 2024
C
Qualcomm AI Engine Direct - Quantizer refine for qat
Chun-I Tsai committed
November 13, 2024
S
Qualcomm AI Engine Direct - support llama3.2 1B/3B with static llama in kv mode
shewu-quic committed
November 7, 2024
H
November 6, 2024
C
Qualcomm AI Engine Direct - Quantizer refine for qat (#6513)
Chun-I Tsai committed
October 28, 2024
C
Qualcomm AI Engine Direct - Set llama io as quantized tensor (#5383)
Chun-I Tsai committed
October 4, 2024
C
add 16a8w matmul custom annotation (#5864)
Chen Lai committed
September 9, 2024
S
Qualcomm AI Engine Direct - Optimization and fix mutable buffer issue (#5072)
shewu-quic committed
August 8, 2024
S
Qualcomm AI Engine Direct - Add source transform for kv cache and sdpa
shewu-quic committed