Skip to content

Commit 497a070

Browse files
PerkzZhengPerkzZheng
authored
[None][update] optimized sparse mla kernels && fix unspecified cuda launch (#8866)
Signed-off-by: Perkz Zheng <[email protected]>
1 parent b4d17d1 commit 497a070

File tree

1,464 files changed

+4418
-4398
lines changed

Some content is hidden

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

1,464 files changed

+4418
-4398
lines changed

‎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 sha256:65b4bfd91a2e48211d5613a3f2baa36862cd8c2880204fe2b9322847ce8d1c9b
3-
size 674929
2+
oid sha256:25e363695ec56d2b74b48a67d2ad3a214c664a33894e2f14428521aef1f74028
3+
size 664199

‎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:eab155475ab87dab2a9b8dcf8caac39eee33529fbd53cd031cd6abb700b30ebb
3-
size 603608
2+
oid sha256:452b9fbe68a5606a6551f450d0ad259b9529d08dd1a0e968768a53ba9d1a5522
3+
size 572380

‎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:e061bc572b0c04d7496a197ed49891b905ebdb750781ff65d559bca9c4c15597
3-
size 657563
2+
oid sha256:86891a3f60bc637ff3c92e4398dc6f5f2d4aa58848d466bf5694fe8d1e778f42
3+
size 648411

‎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 sha256:5cffb056b71065558db88e171ab48de349313e9d13a58f8425dd0497818231f7
3-
size 587822
2+
oid sha256:75a60b5b9779d7b3280745bbc6a1d395587037add8409db103fb37df0193874c
3+
size 555014

‎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:fe07614759abe96bdac7aeea2f466ac8a5f76ead7779cda32ae7203690582605
3-
size 653965
2+
oid sha256:abf75c2b031ca12861475563f3f05e342c795584a18ec2b1e564f3adf07be86b
3+
size 660403

‎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:eecb313f5722654c383351d22e8125a046a792f144cc9720e9fc76021019b151
3-
size 611436
2+
oid sha256:6c0cd50e22ed8a7e551a5893ae1c1d02491ad53a5aff97ddc69f3b467486bb59
3+
size 616296

‎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 sha256:77cb82efcb9b59e13f938cf3af4367890083b516b3c8ee7ddc53f682f30a1528
3-
size 646337
2+
oid sha256:0fb72889f5421ce624a91446680270066f87a8f3fea8ee26ca09fd20b976d087
3+
size 651985

‎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 sha256:5b9518fc0463b41826f71acb3afb490504f8d38d956fdbab7a80618ed802b607
3-
size 605388
2+
oid sha256:6e5e22d30bce9c5c8b4a73dc03df072c5c5f230ae272314918e8e47bdb7b5544
3+
size 611036

‎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 sha256:26585dbebb1a116b1e5bbb964d880f106318b7f9f862c18be32ea3213c63816d
3-
size 670979
2+
oid sha256:3c6f2a245fe4b2deeeda2428b8b8aa028c1254beecb303d957b0bb21f62f6ac6
3+
size 663407

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_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 sha256:33037be671de8f57d48f63978c8a96fa3ffd1174151b810cc27b0fa85b021706
3-
size 602866
2+
oid sha256:0a199cb88469caf3fe70e59cba2ec537e072bcc4b6ba33d5bf9ea7dafbe15416
3+
size 569320

0 commit comments

Comments
 (0)