wangxiyuan
cc1588be50
[Misc] Code clean up ( #1674 )
...
Remove useless function
- vLLM version: v0.9.2
- vLLM main:
b942c094e3wangxiyuan1007@gmail.com >
2025-07-09 08:54:12 +08:00
whx
cd2f14a1b3
[MTP][V1] Adapt mtp with graph mode in v1. ( #1023 )
...
Adapts deepseek mtp with torch air graph mode in v1.
---------
Signed-off-by: whx-sjtu <2952154980@qq.com >
2025-06-09 22:21:42 +08:00
NINGBENZHE
6ec64a3f96
[bugfix] some bugs maybe fail to run ( #896 )
...
### What this PR does / why we need it?
Solve the bug that the graph mode is the same as p and d, and some other
bugs.
### Does this PR introduce _any_ user-facing change?
Wouldn't be
### How was this patch tested?
Follow the end-to-end test
Signed-off-by: ningbenzhe1 <ningbenzhe@huawei.com >
2025-06-03 11:07:33 +08:00
XWFAlone
3442fbdb23
[1/N][UT][v1 MTP] add basic v1 mtp features ( #890 )
...
### What this PR does / why we need it?
add basic v1 mtp features
please merge it after
https://github.com/vllm-project/vllm-ascend/pull/874 and
https://github.com/vllm-project/vllm-ascend/pull/844 .
### Does this PR introduce _any_ user-facing change?
now, we supported basic v1 mtp, only supported tp only、eager mode and
k=1
we will continue to expand more scenarios.
### How was this patch tested?
local tested
Signed-off-by: XWFAlone <xuewenfei2@huawei.com >
Co-authored-by: mengwei805 <mengwei25@huawei.com >
Co-authored-by: JC-ut0 <xuyexiong@huawei.com >
2025-05-30 08:59:58 +08:00
