[Quantization] add humming quantization kernel (#23754)

Co-authored-by: guzekai01 <zekai01@antgroup.com>
Co-authored-by: Julian Huang <huangzhilin.hzl@gmail.com>
Co-authored-by: 墨楼 <huangzhilin.hzl@antgroup.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Peng Zhang <aniz1905@gmail.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
This commit is contained in:
Jinzhen Lin
2026-07-14 08:42:56 +08:00
committed by GitHub
co-authored by guzekai01 Julian Huang 墨楼 Claude Opus 4.8 Peng Zhang Xiaoyu Zhang
parent 4c997310f5
commit 423b8485fb
33 changed files with 2636 additions and 34 deletions
+2 -1
View File
@@ -294,7 +294,8 @@ void moe_align_block_size(
torch::Tensor experts_ids,
torch::Tensor num_tokens_post_pad,
torch::Tensor cumsum_buffer,
bool pad_sorted_token_ids);
bool pad_sorted_token_ids,
bool ignore_invalid_expert);
void topk_softmax(
torch::Tensor& topk_weights,