Skip to content

Commit 064b67e

Browse files
PerkzZhengPerkzZheng
authored
[https://nvbugs/5727952][fix] a pdl bug in trtllm-gen fmha kernels (NVIDIA#9913)
Signed-off-by: Perkz Zheng <[email protected]>
1 parent 0a4c591 commit 064b67e

File tree

1,949 files changed

+9747
-3904
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

1,949 files changed

+9747
-3904
lines changed

‎.pre-commit-config.yaml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1395,6 +1395,8 @@ repos:
13951395
- id: check-symlinks
13961396
- id: detect-private-key
13971397
- id: end-of-file-fixer
1398+
exclude: |
1399+
(?x)^(.*cubin.cpp | .*cubin.h)$
13981400
- id: check-yaml
13991401
args: [--allow-multiple-documents]
14001402
exclude: ".*/gitlab/.*.yml"

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:93da3db51dc2c74c43549079c18247be8c423165c425be80c9b4171624c8a1d7
3-
size 646191
2+
oid sha256:0afc687e183286972166696ff33bedbe8dfa8bc6bdf3213d25ac909e5f3040a9
3+
size 609323

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:d49a0d4280f06012123d03c1f19b2c21eb0884b4621530741c23255c5b1857b9
3-
size 590830
2+
oid sha256:ec9b5930e50e96a57b1c4cdb147dcbc54a484d2a8c8b25fb3587f4bc0378c12c
3+
size 545131

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:abf634eaf82d7c72b7202706c41bbbf1027c049bcd78e899207c77b344b5d47e
3-
size 626655
2+
oid sha256:2ae138ce71c60752175fb660cb30f1633028a0cc3592a30ea2601f50394f87af
3+
size 598271

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:79083440bb77f1423d1b3c33e6ff6e8434a9e95fb803f7a2dfaea1f972eb62c4
3-
size 574254
2+
oid sha256:8dded9944d41cabd7857a6b5ef229e05a843c191774997662029dbf09026a2a3
3+
size 534081

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:56be9d2c764a380d45775cb93ebdc59cf6840267a695ad7910306c316d6e5a6d
3-
size 490794
2+
oid sha256:0759014bf3c82064f8be83eb50850b8da2e90b267f41cfdc969224620c16c6a4
3+
size 460315

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:27fa306c15c04506f2eeb49456ad1920dc3a0ec06cf142f82dab0d3b6d8a5e51
3-
size 457936
2+
oid sha256:3eac32eb1df49520c891b1183e152875e9e22e36fbda48e5708aeaadfd4751a3
3+
size 429011

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:f05b47b2541185087b3d3502a98b6e1fcc50f10ea4f5fbcb173f0a7063392a7b
3-
size 481636
2+
oid sha256:090271f2b5789f2814042c9bd0544d4cf52860fca9d295535d1c5813766da6c9
3+
size 449579

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:5b7ad324102fa900c47b2cb8feaca95cd332b84eea0e6ced413d7da86103ff8e
3-
size 454304
2+
oid sha256:e48501fbee77407818bd30591048da1c6ec16bb69e358b0482ae023c34a3f015
3+
size 425403

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
version https://git-lfs.github.com/spec/v1
2-
oid sha256:a140c2e2014fba58b2789fc18349a9d8ccd361448ff59179ae5839daa414e477
3-
size 638789
2+
oid sha256:221938cece8855eb304e324d4178be760c242d5d79688c1dfdf733a32dbcae64
3+
size 605373

0 commit comments

Comments
 (0)