Skip to content

Opt moe block by dlblas, when ep > 1#3461

Closed
hellozmz wants to merge 1 commit intoInternLM:mainfrom
hellozmz:zmz/lmdeploy_opt_by_dlblas
Closed

Opt moe block by dlblas, when ep > 1#3461
hellozmz wants to merge 1 commit intoInternLM:mainfrom
hellozmz:zmz/lmdeploy_opt_by_dlblas

Conversation

@hellozmz
Copy link

@hellozmz hellozmz commented Apr 21, 2025

4节点测试数据:

Input token throughput (tok/s):

Output len base dlblas 性能变化
1 9638.95 11468.43 +19.0%
32 12263.80 13783.17 +12.4%
64 12641.08 13994.80 +10.7%
128 12512.95 14468.12 +15.6%
512 10759.34 12104.70 +12.5%
1k 8355.66 9178.18 +9.8%
2k 5965.40 6327.07 +6.06%
4k 3711.70 3892.58 +4.9%
8k 1959.26 1937.02 -1.1%
16k 997.58 1012.90 +1.5%
32k 443.81 436.11 -1.7%

Output token throughput (tok/s):

Output len base dlblas 性能变化
1 4.70 5.59 +18.9%
32 192.23 216.04 +12.4%
64 400.91 443.84 +10.7%
128 793.26 917.21 +15.6%
512 2733.50 3075.30 +12.5%
1k 4118.29 4523.69 +9.8%
2k 5918.32 6277.14 +6.06%
4k 7287.26 7642.39 +4.87%
8k 7956.68 7866.38 -1.13%
16k 7796.37 7916.10 +1.54%
32k 7048.98 6926.75 -1.73%

ref: DeepLink-org/DLBlas#24

@hellozmz hellozmz force-pushed the zmz/lmdeploy_opt_by_dlblas branch from 7e7d32a to bcb9807 Compare April 21, 2025 03:43
@hellozmz hellozmz changed the title when ep > 1, opt moe block by dlblas Opt moe block by dlblas, when ep > 1 Apr 21, 2025
@lvhan028 lvhan028 closed this Jul 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants