2 Commits

Author	SHA1	Message	Date
Angazenn	9fbd8017c0	[Quantization]300I Duo support w8a8 quantization (#1560) ... ### What this PR does / why we need it? This pr supports w8a8 on 300I Duo platform. The main change is to use `npu_quant_grouped_matmul_dequant` to replace `npu_grouped_matmul`. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? offline inference on 310p runs normally. --------- Signed-off-by: angazenn <zengyanjia@huawei.com> Signed-off-by: tianyitang <tangtianyi4@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com> Co-authored-by: tianyitang <tangtianyi4@huawei.com>	2025-07-03 22:12:46 +08:00
Zhu Yi Lin	6b80c5acba	Fix W8A8 fused moe bug (#1529) ... ### What this PR does / why we need it? 1. drop some useless code for w8a8 fusedmoe 2. Add in8 kv cache check 3. Add more ut. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed with new added test. --------- Signed-off-by: zhuyilin <809721801@qq.com> Signed-off-by: tianyitang <tangtianyi4@huawei.com> Co-authored-by: tianyitang <tangtianyi4@huawei.com>	2025-07-02 16:40:51 +08:00