Commit History

Static INT8 audio encoder (Entropy calibration, MatMul-only, QOperator format — browser-compatible)
1149262
verified

Reza2kn commited on

Add static INT8 audio encoder (QOperator format, browser-compatible)
f9ccb45
verified

Reza2kn commited on

Add INT8 audio encoder
71f8b93
verified

Reza2kn commited on

GPTQ INT4 decoder_step_int4.onnx.data
f78c065
verified

Reza2kn commited on

GPTQ INT4 decoder_step_int4.onnx
9474add
verified

Reza2kn commited on

GPTQ INT4 decoder_prefill_int4.onnx.data
c0e5047
verified

Reza2kn commited on

GPTQ INT4 decoder_prefill_int4.onnx
8f84081
verified

Reza2kn commited on

Add embedding table (onnx/embed_int8_scales.bin)
b8104e0
verified

Reza2kn commited on

Add embedding table (onnx/embed_int8.bin)
a3ef15b
verified

Reza2kn commited on

Initial upload: INT4 ONNX (encoder + prefill + step) + tokenizer + examples + inference.py
cead59c
verified

Reza2kn commited on