huggingface/text-generation-inference

Pull Requests Commits

feat: add OpenAssistant/oasst-sft-1-pythia-12b to the list of supported models (#122)

OlivierDehaene committed 2 years ago

Verified 6860ce9c

OlivierDehaene committed 2 years ago

Verified 411d6247

feat(python-client): add new parameters (#118)

OlivierDehaene committed 2 years ago

Verified d8dc8f1b

feat(router): add best_of parameter (#117)

OlivierDehaene committed 2 years ago

Verified 55bd4fed

feat(router): support left truncation (#115)

OlivierDehaene committed 2 years ago

Verified e8bfe199

fix(server): do not warp prefill logits (#116)

OlivierDehaene committed 2 years ago

Verified c0795de2

feat: support typical sampling (#114)

OlivierDehaene committed 2 years ago

Verified 1a2d6825

fix(server): fix index out of range for watermarking (#110)

OlivierDehaene committed 2 years ago

Verified 941cd42e

fix(python-client): stream not set on the sync client (#109)

OlivierDehaene committed 2 years ago

Verified 2c5df5d2

feat(launcher): default num_shard to CUDA_VISIBLE_DEVICES if possible (#108)

OlivierDehaene committed 2 years ago

Verified 5fd2dcb5

feat(launcher): allow parsing num_shard from CUDA_VISIBLE_DEVICES (#107)

OlivierDehaene committed 2 years ago

Verified 0ac38d33

fix(server): fix galactica batch (#106)

OlivierDehaene committed 2 years ago

Verified b1485e18

feat(clients): Python client (#103)

OlivierDehaene committed 2 years ago

Verified 3fef90d5

feat: add supported models (#102)

OlivierDehaene committed 2 years ago

Verified 0e9ed1a8

feat: allow local models (#101)

OlivierDehaene committed 2 years ago

Verified cd5961b5

fix(server): fix generate_stream by forcing tokens to be decoded correctly (#100)

OlivierDehaene committed 2 years ago

Verified 9b205d33

OlivierDehaene committed 2 years ago

Verified 1c19b093

feat(server): fix transformers commit (#96)

OlivierDehaene committed 2 years ago

Verified 0b6807ca

fix(launcher): add router parameters to launcher (#95)

OlivierDehaene committed 2 years ago

Verified 240c4187

feat(ci): improve CI speed (#94)

OlivierDehaene committed 2 years ago

Verified e3ded361

feat(server): update to hf_transfer==0.1.2 (#93)

OlivierDehaene committed 2 years ago

Verified 2d39f199

feat(server): add logits watermark (#90)

OlivierDehaene committed 2 years ago

Verified 9b8ea6a6

feat(router): add api-inference headers (#91)

OlivierDehaene committed 2 years ago

Verified f874c478

feat(router): ask hf.co for pipelinetag to decide on compat_return_full_text (#89)

OlivierDehaene committed 2 years ago

Verified 4e685d90

feat(router): add legacy route for api-inference support (#88)

OlivierDehaene committed 2 years ago

Verified 21340f24

fix(server): fix token_is_special (#87)

OlivierDehaene committed 2 years ago

Verified 65e2f162

fix(docs): fix openapi schema (#86)

OlivierDehaene committed 2 years ago

Verified 3b03c4ea

feat(server): add special token bool (#85)

OlivierDehaene committed 2 years ago

Verified 0ac184ce

OlivierDehaene committed 2 years ago

Verified 4b1c9720

feat(server): pre-allocate max attention mask (#75)

OlivierDehaene committed 2 years ago

Verified 44ce098c

Newer Older