 jingchengtianandjingchengtian
|
43ef1e61fb
|
[Perf][TTS] Add per-row generator support to MOSS-TTS talker to eliminate serial fallback for seeded batched requests (#7922)
Signed-off-by: jingchengtian <jingchengtian@users.noreply.github.com>
Signed-off-by: jingchengtian <tjc1995@126.com>
Co-authored-by: jingchengtian <jingchengtian@users.noreply.github.com>
|
2026-09-29 13:13:50 -04:00 |
|
jingchengtian
|
12e9280010
|
[Perf][TTS] Run talker_mtp eagerly when a batch carries explicit seeds (#8009)
Signed-off-by: jingchengtian <tjc1995@126.com>
|
2026-09-28 13:31:48 -04:00 |
|
jingchengtian
|
0b5f8832b9
|
[tts][feature][NPU] Add 2-NPU and 3-NPU disaggregated deploy profiles for MOSS-TTS-Local (#7052)
Signed-off-by: jingchengtian <tjc1995@126.com>
|
2026-09-21 23:14:52 +00:00 |
|
 
|
23f4126445
|
[Hardware][Ascend] Use incremental KV-cache decode for MOSS-TTS depth transformer (#6967)
Signed-off-by: jingchengtian <tjc1995@126.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-09-20 18:34:25 +08:00 |
|
jingchengtian
|
67ef0b64b9
|
[Hardware][Ascend] Use npu_rotary_mul fused kernel for MOSS-TTS codec RoPE (#6908)
Signed-off-by: jingchengtian <tjc1995@126.com>
|
2026-09-02 08:58:23 +00:00 |
|