khalilzhk
|
574572b21b
|
[BugFix] bug fix for DeepSeek eagle3 in Attn-DP mode (#20492)
|
2026-03-19 14:48:46 +08:00 |
|
khalilzhk
|
5f717913a0
|
support Kimi-K2.5-w4a8 on ascend
|
2026-03-10 14:43:27 +08:00 |
|
khalilzhk
|
86eb80007e
|
[NPU] support Kimi-K2.5 on NPU (#19331)
|
2026-02-26 20:41:44 +08:00 |
|
khalilzhk
|
b0a6d5244c
|
[NPU] support dsv32 radixcache on ascend (#17964)
|
2026-02-03 03:34:12 +08:00 |
|
khalilzhk
|
429ef988bc
|
[BugFix] Fix draft model specified config file (#17815)
|
2026-01-31 20:45:36 -08:00 |
|
khalilzhk
|
aca354bcb3
|
[NPU] remove features supported on Ascend NPU (#17455)
|
2026-01-21 11:00:04 +08:00 |
|
khalilzhk
|
9a628744fc
|
[CI] fix piecewise graph test case on ascend (#16933)
|
2026-01-12 20:16:30 +08:00 |
|
khalilzhk
|
948b6acee8
|
[BugFix] fix prefixcache performance and accuracy on ascend (#13573)
|
2025-12-08 02:16:20 +08:00 |
|
 
|
2d531946db
|
[Ascend][feature] support L1+ L2 radixcache on ascend (#12214)
Co-authored-by: khalilzhk <zhangkaikai12@huawei.com>
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
|
2025-11-12 20:45:24 +08:00 |
|