- 19 Nov, 2025 1 commit
-
-
Kane authored
Feature: 1. added mlu590 bfloat16, single-gpu and multi-gpus inference. 2. added mlu590 int8 inference.
-
- 14 Nov, 2025 1 commit
-
-
gushiqiao authored
-
- 10 Nov, 2025 2 commits
-
-
helloyongyang authored
-
helloyongyang authored
-
- 07 Nov, 2025 2 commits
-
-
Yang Yong (雍洋) authored
-
helloyongyang authored
-
- 06 Nov, 2025 1 commit
-
-
STwangyingrui authored
Co-authored-by:
root <root@pt-2ec29e323c56463f8ad6d292b6047107-worker-0.pt-2ec29e323c56463f8ad6d292b6047107.ns-devsft-3460edd0.svc.cluster.local> Co-authored-by:
gushiqiao <975033167@qq.com>
-
- 03 Nov, 2025 1 commit
-
-
Yang Yong (雍洋) authored
-
- 01 Nov, 2025 1 commit
-
-
Yang Yong (雍洋) authored
-
- 30 Oct, 2025 1 commit
-
-
gushiqiao authored
Co-authored-by:gushiqiao <975033167@qq.ocm>
-
- 23 Oct, 2025 1 commit
-
-
Rongjin Yang authored
https://github.com/Linboyan-trc/SpargeAttn/tree/02_develop need install --------- Co-authored-by:
Yang Yong (雍洋) <yongyang1030@163.com>
-
- 21 Oct, 2025 1 commit
-
-
Yang Yong (雍洋) authored
-
- 17 Oct, 2025 1 commit
-
-
Yang Yong (雍洋) authored
-
- 15 Oct, 2025 1 commit
-
-
Yang Yong (雍洋) authored
-
- 09 Oct, 2025 1 commit
-
-
gushiqiao authored
-
- 27 Sep, 2025 1 commit
-
-
gushiqiao authored
-
- 15 Sep, 2025 3 commits
-
-
Watebear authored
-
Yang Yong(雍洋) authored
-
gushiqiao authored
-
- 02 Sep, 2025 1 commit
-
-
gushiqiao authored
-
- 29 Aug, 2025 1 commit
-
-
Yang Yong(雍洋) authored
* update seko talk * update * Update configs * update --------- Co-authored-by:
-
- 21 Aug, 2025 2 commits
- 06 Aug, 2025 1 commit
-
-
gushiqiao authored
-
- 05 Aug, 2025 2 commits
- 01 Aug, 2025 2 commits
-
-
gushiqiao authored
-
helloyongyang authored
-
- 31 Jul, 2025 1 commit
-
-
helloyongyang authored
-
- 28 Jul, 2025 2 commits
-
-
gushiqiao authored
-
helloyongyang authored
-
- 16 Jul, 2025 1 commit
-
-
gushiqiao authored
-
- 10 Jul, 2025 1 commit
-
-
gushiqiao authored
-
- 09 Jul, 2025 1 commit
-
-
gushiqiao authored
-
- 03 Jul, 2025 1 commit
-
-
wangshankun authored
-
- 02 Jul, 2025 1 commit
-
-
gushiqiao authored
Enable 720p model inference on low-spec GPUs/CPUs and accelerate T5/CLIP quantized models with vLLM operators
-
- 16 Jun, 2025 1 commit
-
-
gushiqiao authored
-
- 12 Jun, 2025 1 commit
-
-
Zhuguanyu Wu authored
* add step & cfg distillation wan model * bug fixed
-
- 09 Jun, 2025 1 commit
-
-
gushiqiao authored
* reconstruct quantization and fix memory leak bug. * Support lazy load inference. * reconstruct quantization * Fix hunyuan bugs * deleted tmp file --------- Co-authored-by:
root <root@pt-c0b333b3a1834e81a0d4d5f412c6ffa1-worker-0.pt-c0b333b3a1834e81a0d4d5f412c6ffa1.ns-devsft-3460edd0.svc.cluster.local> Co-authored-by:
gushiqiao <gushqiaio@sensetime.com> Co-authored-by:
gushiqiao <gushiqiao@sensetime.com>
-
- 13 May, 2025 1 commit
-
-
TorynCurtis authored
* function hunyuan_t2v_tea, hunyuan_t2v_taylorseer, modify the fresh_threshold of taylorseer * hunyuan i2v,t2v + tea,tay; wan i2v,t2v + tea function, add log files * 删除了TeaCace Scheduler的多余属性 * 删除了多余目录 * 修复了TeaCaching部分的bug,目前t2v, i2v feature caching均可跑通 * Update attn_weight.py --------- Co-authored-by:
-
