Add QuantizeEmbeddingInt8 and ShareEmbeddingLmHead graph surgeries for INT8 embedding quantization#2464
Open
apsonawane wants to merge 4 commits into
Open
Add QuantizeEmbeddingInt8 and ShareEmbeddingLmHead graph surgeries for INT8 embedding quantization#2464apsonawane wants to merge 4 commits into
apsonawane wants to merge 4 commits into
