huggingface/transformers

Pull Requests Commits

adding loading time

3outeille committed 99 days ago

13af720b

add rowwise input

3outeille committed 100 days ago

f8ee46bd

Merge branch 'split/b-pr-0-dual-path-tp' into bench-dtensor-vs-legacy-tp

3outeille committed 100 days ago

Verified 811246d0

Merge branch 'main' into split/b-pr-0-dual-path-tp

3outeille committed 100 days ago

Verified c1bc2ca0

3outeille committed 100 days ago

5fef89f0

refactor MoEExperParallel

3outeille committed 100 days ago

e815a7c4

3outeille committed 100 days ago

e62209e1

3outeille committed 100 days ago

661aad68

refactor colwise

3outeille committed 100 days ago

a1f8a483

🚨 [cache] Cropping can only be done with negative values (#47720)

Cyrilvallez committed 100 days ago

Verified d24d79da

Remove dangling files and folders (#47764)

Cyrilvallez committed 100 days ago

Verified 54b89a25

Fix AI-written conversion mappings (#47755)

Cyrilvallez committed 100 days ago

Verified 3794477e

[generate] Stop setting the static cache as an attribute to save memory (#47731)

Cyrilvallez committed 100 days ago

Verified 9f66415a

[Mistral] Add native tekken tokenizer support to AutoTokenizer (#47507)

juliendenize committed 100 days ago

Verified 7c382b62

update mistral common version for PR 47507 (#47677)

itazap committed 100 days ago

Verified 4806a9b1

Fix spelling/grammar in model files (batch 3/3) (#47684)

Rocketknight1 committed 101 days ago

Verified 92d02b50

Fix spelling/grammar in core library, examples, and utils (#47685)

Rocketknight1 committed 101 days ago

Verified 9451e3ab

Fix spelling/grammar in model files (batch 2/3) (#47683)

Rocketknight1 committed 101 days ago

Verified ff886afa

update sonicmoe versions (#47769)

IlyasMoutawwakil committed 101 days ago

Verified 38ffcde1

clean up reverse_op fixme in compressed_tensors (#47701)

DhanushPillay committed 101 days ago

Verified 2481a7b9

PR CI with torch 2.13 (#47767)

ydshieh committed 101 days ago

Verified 49140dd1

Import utils compilation fixes (#47726)

IlyasMoutawwakil committed 101 days ago

Verified 410c4b17

Fix DBRX MoE hidden size and expert GLU transposes (#47671)

kaixuanliu committed 101 days ago

Verified 2ce15881

Fix multi token decode merging (#47762)

IlyasMoutawwakil committed 101 days ago

Verified cf8572d3

Fix: Remove redundant @can_return_tuple conflicting with @capture_out… (#47733)

guarin committed 101 days ago

Verified 66799f45

Modularize qwen-format vision processors (#47573)

zucchini-nlp committed 101 days ago

Verified bed02e1f

fix processor config nested key fallback (#47628)

YunzhuLu committed 101 days ago

Verified c62820a7

[CI - Debug] Skip /transformers-dependent steps for CPU runner (#47759)

ydshieh committed 101 days ago

Verified 9302fe06

[CI] Add CPU runner support to ssh-runner workflow (#47757)

ydshieh committed 101 days ago

Verified d31667f4

Simplify reverse weight conversion (#47725)

Cyrilvallez committed 101 days ago

Verified f831d9c5

Older