Issues: tenstorrent/tt-metal
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Incremental build failure with CMake + Ninja
bug
Something isn't working
P2_should_have
#8580
opened May 17, 2024 by
TT-billteng
Fix Clang-17 post-commit
infra-ci
infrastructure and/or CI changes
#8579
opened May 16, 2024 by
vtangTT
3 tasks
[llama] implement rotary_embeddings_llama op
llama2-70b
LLM_feature
LLMs on Metal
#8577
opened May 16, 2024 by
mikevin920
Having DPRINTs in kernels affects perf even when not enabled
bug
Something isn't working
P1_critical
perf
for issues tracking performance problems/improvements
#8575
opened May 16, 2024 by
tt-aho
[optimization] CCL Allgather - short-circuit worker <-> worker communication
op_cat: ccl
P2_should_have
#8574
opened May 16, 2024 by
SeanNijjar
CCL Optimization (Allgather, Reduce Scatter)
op_cat: ccl
P2_should_have
#8573
opened May 16, 2024 by
SeanNijjar
Depth-wise 1D convolution needed for Mamba prefill
LLM_feature
mamba
P1_critical
prefill
LLM models have prefill mode and it's optimization is usually separated from decode mode.
#8571
opened May 16, 2024 by
esmalTT
Handle static and dynamic OP validation performantly
P1_critical
ttnn
#8569
opened May 16, 2024 by
davorchap
Add sweep tests for split_query_key_value_and_split_heads
cleanup
P2_should_have
#8563
opened May 16, 2024 by
sjameelTT
[llama] 40 cores QKV matmul & BMM rotary matrix matmul
llama2-70b
LLM_feature
LLMs on Metal
#8561
opened May 16, 2024 by
mikevin920
Move t3k building into build runners and migrate t3k post commit pipeline to unit tests
infra-ci
infrastructure and/or CI changes
P1_critical
#8558
opened May 16, 2024 by
tapspatel
Remove gdb build and documentation assets because it's not used and doesn't work
docs
Improvements or additions to documentation
infra-ci
infrastructure and/or CI changes
P2_should_have
#8557
opened May 16, 2024 by
tt-rkim
Investigate ttnn resnet 50 batch_size 8 failure on fast dispatch nightly
ci-bug
bugs found in CI
P1_critical
ResNet-50
#8555
opened May 16, 2024 by
tt-rkim
ttnn.eq incorrect output for uint16 tensors
bug
Something isn't working
P1_critical
#8551
opened May 16, 2024 by
sraizada-tt
Update INSTALLING.md for docker instructions
docs
Improvements or additions to documentation
#8550
opened May 16, 2024 by
ttmchiou
support 1D tensors in ttnn
moreh
moreh contribution
P1_critical
ttnn
#8541
opened May 15, 2024 by
davorchap
Eltwise binary EQ should produce a boolean or integer tensor as output
moreh
moreh contribution
P1_critical
#8540
opened May 15, 2024 by
davorchap
Add queue_id to the MNIST OPs
moreh
moreh contribution
P1_critical
#8539
opened May 15, 2024 by
davorchap
Option to allow use of multiple-producer SW queue mode
moreh
moreh contribution
P1_critical
#8538
opened May 15, 2024 by
davorchap
Move ttnn.as_tensor, ttnn.from_tensor and ttnn.to_torch to C++
#8537
opened May 15, 2024 by
arakhmati
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.