Skip to content

Commit 62b6693

Browse files
VALLIS-NERIAmikeiovine
VALLIS-NERIA
authored and
mikeiovine
committed
[https://nvbugs/5541494] [fix] Fix missing sm100f/103a kernels and add tests (NVIDIA#8098)
Signed-off-by: Xiwen Yu <[email protected]>
1 parent e91196b commit 62b6693

File tree

66 files changed

+2934
-429
lines changed

Some content is hidden

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

66 files changed

+2934
-429
lines changed

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/BatchedGemmInterface.h‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -548,7 +548,6 @@ class BatchedGemmInterface
548548
// Aligns the pointer to the alignment
549549
template <typename Dtype>
550550
inline Dtype* alignPtr(Dtype* ptr, int64_t alignment) const;
551-
552551
// Returns the size of the workspace buffers in bytes
553552
std::vector<size_t> getWorkspaceSizesInBytes(BatchedGemmConfig const& config, BatchedGemmData const& data) const;
554553

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/KernelMetaInfo.h‎

Lines changed: 2742 additions & 428 deletions
Large diffs are not rendered by default.

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedP2x1x2x3_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:f917197d94cb7f6342be8d6217ed844731eb2978c8da6af45f685d2ed85ceedd
3+
size 551613

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:c729b9bfec564e9418637d2dd8adaaba2dcf0411b3d63faf979bf8371f7d33af
3+
size 447407

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedP2x1x2x3_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:9ddfda9c41677daf3ee47958eb7b967e56b1521352133ef3a5e280ef45aee5ce
3+
size 556695

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:fecc181591d440ab29e3f54ee2483fb2e0e0312ff7515b7e2f6687a0fa5b0bf6
3+
size 453279

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedP2x1x2x3_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:5b4782ce0968cb0f5238735940279368e8d7f502d4346f5d75ec595d76efb0a3
3+
size 577419

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:bcc9a026849dd612ea6db4300d753d56ec1ebd81f0a666c0e6e39ae03d746912
3+
size 470549

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedP2x1x2x3_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:7bc653efc7c50fe1b31e1cd4c13459f8327a6378f38757de2f7839d9cf71c662
3+
size 582501

‎cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_rM_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100f_cubin.cpp‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:8502c65de339a15a10f2b69316b0996969af6d703ff44fad3525820b1a6ee582
3+
size 476419

0 commit comments

Comments
 (0)