issues
search
ROCm
/
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
http://pytorch.org
Other
219
stars
50
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[release/1.13] Fix test_oom_tracing by increasing tensor size
#1453
dnikolaev-amd
closed
11 hours ago
0
[release 2.0] Fix test_oom_tracing by increasing tensor size for
#1452
dnikolaev-amd
closed
12 hours ago
0
[release/2.2] fix test_oom_tracing and skip test_profiler_ cuda_sync_events
#1451
dnikolaev-amd
closed
12 hours ago
0
[release/2.3] Fix test_oom_tracing by increasing tensor size
#1450
dnikolaev-amd
closed
12 hours ago
0
[rocm6.3_internal_testing] Fix test_oom_tracing by increasing tensor size
#1449
dnikolaev-amd
closed
12 hours ago
0
[NO CP] [Inductor] Use torch.version.hip to conditionalise out dynamic rblock scaling
#1448
jataylo
closed
12 hours ago
1
Ck template
#1447
alugorey
closed
6 days ago
0
Compilation Fail "undefined reference to 'unwind_c'" PyTorch Build with Python3.11 ROCm WSL2
#1446
unclemusclez
opened
6 days ago
0
CK gemm header
#1445
alugorey
closed
1 week ago
0
[release/2.1] fix test_vmapvjpvjp and skip test_profiler_experimental_tree
#1444
ramcherukuri
closed
1 week ago
0
[rocm6.3_internal_testing] Update apex commit to pick up wheel-related changes
#1443
jithunnair-amd
closed
1 week ago
0
[release/2.1] Update apex commit to pick up wheel-related changes
#1442
jithunnair-amd
closed
1 week ago
0
[release/2.2] Update apex commit to pick up wheel-related changes
#1441
jithunnair-amd
closed
1 week ago
0
[release/2.3] Update apex commit to pick up wheel-related changes
#1440
jithunnair-amd
closed
1 week ago
0
SWDEV-469009 - skips for flaky distributed tests
#1439
pragupta
closed
1 week ago
0
[release/2.3] Update apex branch and commit
#1438
jithunnair-amd
closed
2 weeks ago
0
Support 6.2 AMDSMI API changes for clock speed
#1437
jataylo
closed
1 week ago
1
IFU for rocm6.3_internal_testing
#1436
dnikolaev-amd
closed
1 week ago
3
[ROCm] Intra-node all reduce initial implementation
#1435
jataylo
closed
2 weeks ago
2
Scale XBLOCK in triton reduction configs to avoid hitting max grid
#1434
jataylo
closed
2 weeks ago
1
Print consolidated log file for pytorch unit test automation scripts
#1433
jithunnair-amd
closed
3 weeks ago
1
[SWDEV-464578] [AMD] Fix deprecated amdsmi api (#126962)
#1432
jataylo
closed
3 weeks ago
0
Tunableop improvements: record untuned gemm and provide a API to tune them offline
#1431
jfactory07
closed
3 weeks ago
0
Mitigates SWDEV-459618
#1430
xinyazhang
opened
1 month ago
0
AMDSMI integration into 6.2_internal_testing branch
#1429
jataylo
closed
1 month ago
0
Fix SWDEV-459623
#1428
xinyazhang
closed
1 month ago
0
Fix SWDEV-459621.
#1427
xinyazhang
closed
1 month ago
1
don't check memory format for empty tensors (#126593)
#1426
pragupta
closed
1 month ago
0
[release/1.10.1] Remove references to `pkg_resources.packaging`
#1425
jithunnair-amd
closed
1 month ago
0
[release/1.13] Remove references to `pkg_resources.packaging`
#1424
jithunnair-amd
closed
1 month ago
0
[release/2.0] Remove references to `pkg_resources.packaging`
#1423
jithunnair-amd
closed
1 month ago
0
[release/2.1] Remove references to `pkg_resources.packaging`
#1422
jithunnair-amd
closed
1 month ago
0
Enable fp8 inductor unit tests
#1421
alugorey
closed
1 month ago
0
skip vmapvjpvjp_linalg_householder_product_cuda_float32
#1420
alugorey
closed
1 month ago
0
Enable e5m2 x e4m3 test in test_float8_scale
#1419
alugorey
closed
1 month ago
0
PR #1255 to rocm6.2 release
#1418
ramcherukuri
closed
1 month ago
0
[ROCm] skip warp update to 64 for gfx10 and gfx11
#1417
ramcherukuri
closed
1 month ago
1
Added cublasGemmAlgo_t -> hipblasGemmAlgo_t
#1416
rraminen
closed
1 month ago
0
Rework test_float8_basics for current ROCm support
#1415
alugorey
closed
1 month ago
0
[NO CP] Update the hipsparse sampled addmm condition for release/2.2
#1414
dnikolaev-amd
closed
1 month ago
0
Added gcnArchName
#1413
BLOrange-AMD
closed
1 month ago
0
Added a fraction parameter for profiler_oom_tracing
#1412
BLOrange-AMD
closed
1 month ago
0
Added a fraction parameter for profiler_oom_tracing
#1411
BLOrange-AMD
closed
1 month ago
0
[release/2.2] Include ROCm patch version unconditionally in triton version
#1410
jithunnair-amd
closed
2 months ago
0
Supported allreduce sparse
#1409
BLOrange-AMD
closed
2 months ago
0
Implementing own quite naive gemv kernel as replacement of default used in nn.Linear gives 20% better speed on MI100
#1408
Epliz
opened
2 months ago
0
torch multinomial causes severe stall in Hugginface Transformers LLM generation
#1407
Epliz
opened
2 months ago
1
[ROCm] Integrate hipblasLT AMAX_D pointer
#1406
alugorey
closed
1 month ago
0
[release/2.3] Update triton dependency
#1405
jithunnair-amd
closed
2 months ago
0
Excluded inductor tests on certain GPU arch - follow up
#1404
BLOrange-AMD
closed
2 months ago
3
Next