microsoft/DeepSpeed

Pull Requests Commits

Update python to re-enable 3.11 and 3.12 tests

loadams committed 129 days ago

62c51a41

Use `torch.log1p` (#6930)

kit1980 committed 130 days ago

Verified c41b0c28

inference: remove unused _validate_args function (#5505)

nelyahu committed 130 days ago

Verified c7f30322

Check transformers version in BLOOM for inference v1 (#6766)

lekurile committed 131 days ago

Verified f2cc8090

Cleanup ops/transformer/inference tests (#6925)

loadams committed 131 days ago

Verified c348c5b1

Reduce the device bubble introduced by heavy loop synchronization in coalesced fetch/release(z3_leaf_module) (#6694)

inkcherry committed 131 days ago

Verified b0040b6c

Add fp8_gemm fallback for non-triton systems (#6916)

oelayan7 committed 131 days ago

Verified c5e48f49

[BUG FIX]:fix get torch.version.cuda error when cuda is None in rocm (#6909)

hj-wei committed 131 days ago

Verified f8c9f314

Fix `checkpointable_layers` Logic (#6881)

Quentin-Anthony committed 134 days ago

Verified 0dbbb70b

Cleanup ops/transformer/inference tests (#6830)

loadams committed 134 days ago

Verified a8ede3a9

Stage3: Use new torch grad accumulation hooks API (#6773)

deepcharm committed 134 days ago

Verified 456c9ac6

Change compile for pipeline module torch.compile (#6478)

NirSonnenschein committed 138 days ago

Verified 3573858e

Update Gaudi2 jobs to latest 1.19 build (#6905)

raza-sikander committed 142 days ago

Verified cc03c76d

Fix error caused by all_reduce call in domino (#6880)

hwchen2017 committed 142 days ago

Verified 85cc5f9b

hpu_accelerator: use torch.use_deterministic_algorithms (#6897)

nelyahu committed 149 days ago

Verified eea53048

Zero2: avoid graph breaks in torch.compile by using param_idx (#6803)

nelyahu committed 149 days ago

Verified 00ea0c46

Allow to compile collective for PT>2.3 (#6899)

NirSonnenschein committed 149 days ago

Verified 4fd79205

Update version.txt after 0.16.2 release (#6893)

loadams committed 150 days ago

Verified f9e158a0

Update code owners (#6890)

tjruwase committed 150 days ago

Verified b344c04d

Add arctic model support by adding w2 to all_reduce (#6856)

pi314ever committed 150 days ago

Verified 0b25630a

Don't error out when cpu accelerator doesn't have torch (as default for whl building) (#6886)

loadams committed 151 days ago

Verified 4cd1d974

Update transformers ops unit tests to use `requried_torch_version` (#6884)

loadams committed 151 days ago

Verified 2f32966b

Fix --enable_each_rank_log when used with PDSH multi-node runner (#6863)

akeshet committed 151 days ago

Verified a964e435

Add MLP/lm_head tp grain size setting. (#6828)

Yejing-Lai committed 152 days ago

Verified da771ed4

Remove pin from transformers version and fix Processing/Threading issues in tests (#6822)

loadams committed 152 days ago

Verified 87c65068

Fix assertion for offloading states (#6855)

tohtana committed 152 days ago

Verified db98cc3a

Update real_accelerator.py (#6845)

keiwoo committed 155 days ago

Verified fc7c0700

Remove warnings from autodoc and sphinx (#6788)

loadams committed 155 days ago

Verified 6e3e13cb

Update TSC (#6867)

tjruwase committed 155 days ago

Verified 8efbcc49

add domino navigation (#6866)

GuanhuaWang committed 155 days ago

Verified b5e3fac6

Older