 Estrella-xx
|
4c2c169e6b
|
[NPU]Strip padding before FIA kernel for vision encoder padded sequences (#36329)
|
2026-09-01 19:28:19 +08:00 |
|
|
Estrella-xx
|
c98f1ccedb
|
[NPU]Ensure tensors allocated by empty_like are contiguous (#34935)
|
2026-08-20 20:40:57 +08:00 |
|
|
Estrella-xx
|
eea2e5d6e5
|
Optimize delayed sample and mrope position computation (#32637)
|
2026-08-13 19:15:47 +08:00 |
|
|
Estrella-xx
|
bac351d617
|
[NPU] Fix block_table batch size mismatch in GLM-4.7-Flash DeepEP + MTP without CUDA Graphs (#29829)
|
2026-07-02 11:09:01 +08:00 |
|
|
Estrella-xx
|
c6a7c98ae4
|
[NPU]GLM-4.7-Flash optimize with fused kernels (#29509)
|
2026-06-30 19:22:19 +08:00 |
|
|
Estrella-xx
|
2a9cce5d27
|
[NPU] Add MTP support for GLM-4.7-Flash (#28516)
|
2026-06-18 17:54:06 +08:00 |
|
|
Estrella-xx
|
6abef38627
|
[NPU]adaptation to support deterministic inference (#21197)
|
2026-06-09 09:22:09 +08:00 |
|