vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-05-05 23:50:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

[feat](kt-kernel): CPU-GPU experts sched (#1796)
Some checks failed
Book-CI / test (push) Has been cancelled
Details
Book-CI / test-1 (push) Has been cancelled
Details
Book-CI / test-2 (push) Has been cancelled
Details
Deploy / deploy (macos-latest) (push) Has been cancelled
Details
Deploy / deploy (ubuntu-latest) (push) Has been cancelled
Details
Deploy / deploy (windows-latest) (push) Has been cancelled
Details

Browse source
This commit is contained in:
Jianwei Dong 2026-01-16 17:01:15 +08:00 • committed by GitHub
parent 6277da4c2b
commit 027832c590
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 687 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

6
kt-kernel/test/per_commit/test_moe_amx_bench_int8.py
View file

@ -34,13 +34,13 @@ except ImportError as e:
import_error = str(e)
# Test parameters (from original bench_moe_amx.py)
expert_num = 16
expert_num = 128
hidden_size = 7168
intermediate_size = 2048
max_len = 25600
num_experts_per_tok = 8
num_experts_per_tok = 0
layer_num = 2
qlen = 2048
qlen = 1
warm_up_iter = 1000
test_iter = 2000