Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hf_text-generation-inference/server/pyproject.toml

46 lines
1.2 KiB
TOML
Raw Normal View History

Init
2022-10-08 04:30:12 -06:00
[tool.poetry]
feat(clients): Python client (#103)
2023-03-07 10:52:22 -07:00
name = "text-generation-server"
v0.9.0 (#525)
2023-07-01 11:25:41 -06:00
version = "0.9.0"
feat(router): refactor API and add openAPI schemas (#53)
2023-02-03 04:43:37 -07:00
description = "Text Generation Inference Python gRPC Server"
Init
2022-10-08 04:30:12 -06:00
authors = ["Olivier Dehaene <olivier@huggingface.co>"]
feat: Improve error handling
2022-10-17 06:59:00 -06:00
[tool.poetry.scripts]
feat(clients): Python client (#103)
2023-03-07 10:52:22 -07:00
text-generation-server = 'text_generation_server.cli:app'
feat: Improve error handling
2022-10-17 06:59:00 -06:00
Init
2022-10-08 04:30:12 -06:00
[tool.poetry.dependencies]
python = "^3.9"
protobuf = "^4.21.7"
feat(launcher): Log server stdout (#19) Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-01-05 04:01:23 -07:00
grpcio = "^1.51.1"
grpcio-status = "^1.51.1"
grpcio-reflection = "^1.51.1"
grpc-interceptor = "^0.15.0"
Init
2022-10-08 04:30:12 -06:00
typer = "^0.6.1"
chore(sever): update requirements (#357) Fixes #338
2023-05-23 10:03:22 -06:00
accelerate = { version = "^0.19.0", optional = true }
fix(docker): remove unused dependencies (#205)
2023-04-19 11:39:31 -06:00
bitsandbytes = { version = "^0.38.1", optional = true }
chore(server): update safetensors version (#235)
2023-04-25 05:50:56 -06:00
safetensors = "0.3.1"
feat(launcher): Log server stdout (#19) Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-01-05 04:01:23 -07:00
loguru = "^0.6.0"
feat: add distributed tracing (#62)
2023-02-13 05:02:45 -07:00
opentelemetry-api = "^1.15.0"
opentelemetry-exporter-otlp = "^1.15.0"
opentelemetry-instrumentation-grpc = "^0.36b0"
feat(server): update to hf_transfer==0.1.2 (#93)
2023-03-03 03:26:27 -07:00
hf-transfer = "^0.1.2"
feat(server): add flash attention llama (#144)
2023-04-11 08:38:22 -06:00
sentencepiece = "^0.1.97"
tokenizers = "0.13.3"
feat(server): Rework model loading (#344) # What does this PR do? Reworked the loading logic. Idea is to use cleaner loading code: - Remove need for `no_init_weights` - Remove all weird `bnb_linear` and `load_weights` and `post_load_weights`. New code layout: - New class `Weights` in charge of handling loading the weights from multiple files into appropiate tensors (potentially sharded) - TP layers now are "shells", they contain the code to know what kind of sharding we need + eventual `all_reduce`. They do not inherit from linear, but they contain some kind of Linear instead - the contained linear can be either FastLinear, BnbLinear or GPTq Linear next. - All modeling code is explictly made for sharding, process group is just no-ops for non sharded code (removes a lot of test cases) ![Screenshot from 2023-05-19 23-19-59](https://github.com/huggingface/text-generation-inference/assets/204321/9a802654-74a3-488c-87a8-073743a6143f) --------- Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.taildb5d.ts.net> Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.ec2.internal> Co-authored-by: OlivierDehaene <olivier@huggingface.co> Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
2023-06-08 06:51:52 -06:00
huggingface-hub = "^0.14.1"
transformers = "^4.29.2"
feat(server): Add Non flash MPT. (#514) # What does this PR do? This adds a non flash version of MPT. Flash is harder because we need to create a bias ready cuda kernel of flash attention. Fixes https://github.com/huggingface/text-generation-inference/issues/361 Fixes https://github.com/huggingface/text-generation-inference/issues/491 Fixes https://github.com/huggingface/text-generation-inference/issues/290
2023-07-03 05:01:46 -06:00
einops = "^0.6.1"
Init
2022-10-08 04:30:12 -06:00
feat(server): Support all AutoModelForCausalLM on a best effort basis
2022-10-28 11:24:00 -06:00
[tool.poetry.extras]
fix(docker): remove unused dependencies (#205)
2023-04-19 11:39:31 -06:00
accelerate = ["accelerate"]
feat(server): Support all AutoModelForCausalLM on a best effort basis
2022-10-28 11:24:00 -06:00
bnb = ["bitsandbytes"]
Init
2022-10-08 04:30:12 -06:00
[tool.poetry.group.dev.dependencies]
feat: add distributed tracing (#62)
2023-02-13 05:02:45 -07:00
grpcio-tools = "^1.51.1"
fix(ci): fix CVE in github-slug-action (#174)
2023-04-13 04:43:05 -06:00
pytest = "^7.3.0"
Init
2022-10-08 04:30:12 -06:00
fix(server): fix init for flash causal lm (#352) Fixes #347
2023-05-22 07:05:32 -06:00
[tool.pytest.ini_options]
markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"]
Init
2022-10-08 04:30:12 -06:00
[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"