Pull requests: microsoft/DeepSpeed
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix Stable-Diffusion: Add correct memory-allocation at DeepSpeed-Attention
#2474
opened Nov 3, 2022 by
RezaYazdaniAminabadi
Loading…
Prototype DS inference config. Tested with gpt2/bert. (#2459)
#2472
opened Nov 3, 2022 by
awan-10
Loading…
Collect unique CUDA graphs for Unique Input Signatures
#2458
opened Oct 31, 2022 by
cmikeh2
Loading…
Inference support for encoder-decoder architecture
#2451
opened Oct 28, 2022 by
RezaYazdaniAminabadi
•
Draft
Implement apply_rotary_pos for rotate_half and rotary_dim > 32 in transformer inference
#2448
opened Oct 27, 2022 by
twaka
Loading…
Reflect use_parallel_residual in mlp_after_attn for module_inject
#2446
opened Oct 26, 2022 by
twaka
Loading…
support iterators with incompletely defined __len__ functions
#2445
opened Oct 25, 2022 by
codedecde
Loading…
Generic loading of checkpoints in deepspeed-inference
#2405
opened Oct 7, 2022 by
RezaYazdaniAminabadi
•
Draft
Fix error in get_model_profile when output_file argument is a relative path without a prefix
hacktoberfest-accepted
#2383
opened Oct 2, 2022 by
bstee615
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.