Skip to content
GitLab
Explore
Sign in
不巧我在等你
2025pra_WaitingForYou
Repository
Branches
Overview
Active
Stale
All
main
default
protected
339474a9
·
initial submission
·
Jul 07, 2026
xlang-block-64
102d265b
·
Block_m from 16 to 64
·
Jul 10, 2026
xlang-blockm64-prefill64
930eb0ec
·
Turn prefill back to 32 becauce 64 cause RE
·
Jul 11, 2026
xlang-blockm64-decodeBLOCK32
141b6786
·
Block_m 64 AND decode BLOCK=32
·
Jul 11, 2026
zjy-test2
a316c247
·
还是64比较好
·
Jul 11, 2026
xlang-blockm64-kvblock32
cde31dcf
·
Block_m 64 AND rocm.py kvblock from 16 to 32
·
Jul 11, 2026
xlang-blockm-adaptive128
668d22af
·
Block_m switch 64 and 128
·
Jul 12, 2026
xlang-blockm-128
5a234684
·
Block_m is all 128
·
Jul 12, 2026
xlang-blockm-48
6351101a
·
Block_m is all 48
·
Jul 12, 2026
xlang-blockm64-num_warps4
b3adb7a0
·
num_warps=4
·
Jul 12, 2026
xlang-blockm64-aiter
56a5057c
·
Enable ROCm AITER by default
·
Jul 12, 2026
xlang-blockm64-batch8192
ac2ef161
·
Tune ROCm prefill token budget for long prompts
·
Jul 12, 2026
xlang-blockm64-gdnchunk32
616b99a9
·
Tune ROCm GDN prefill chunk size
·
Jul 12, 2026
zjy-test3
eb3b4c64
·
解决_init_scale_buffers没被调用
·
Jul 13, 2026
xlang-blockm64-gdn-h-warp8
7a2bb1fd
·
Expand ROCm GDN state kernel autotuning
·
Jul 13, 2026
zjy-test1
298c544f
·
test1修为64
·
Jul 13, 2026
xlang-blockm64-gdn-decode-warp2
e96c92d9
·
Tune ROCm GDN packed decode parallelism
·
Jul 13, 2026
xlang-blockm64-gdn-o-stage1
848e0b32
·
Expand ROCm GDN output kernel staging autotune
·
Jul 13, 2026
xlang-blockm64-gdn-kkt-stage1
6f701c10
·
Expand ROCm GDN KKT kernel staging autotune
·
Jul 13, 2026
xlang-blockm64-rocm-native-paged
8827f3c5
·
Enable ROCm split attention for native paged decode
·
Jul 13, 2026
Prev
1
2
Next