* docs: add AWS (EC2/SageMaker) deployment + benchmarking guide
- Add an AWS deployment tutorial for EC2 + SageMaker
- Fix SageMaker example indentation and link to the new guide
- Add the new guide to the docs toctree
* docs: address AWS deployment review feedback
* Apply suggestion from code review
---------
Co-authored-by: Fahad Alghanim <[email protected]>
Co-authored-by: Alvaro Bartolome <[email protected]>
* chore: prepare version 3.3.5
* black
* neuron: black
* Update hf-xet in uv lockfile
* Attempt to fix API doc check failure
Add `error_type` where missing.
* Pin redocly version
* Sync redocly with Nix for now
---------
Co-authored-by: Daniël de Kok <[email protected]>
* Disable Cachix pushes
This is not safe until we have sandboxed builds. For TGI alone
this might not be a huge issue, but with Cachix caching disabled
in hf-nix, TGI CI would build all the packages and push it to
our cache.
* fix: bump docs
---------
Co-authored-by: drbh <[email protected]>
* Add json_schema alias for GrammarType
* Add tests for all aliases
* fix: various linter adjustments
* fix: end-of-file-fixer lint
* fix: add test snapshots and avoid docs change
* fix: another end-of-file-fixer lint
* feat: support json_schema grammar constraining and add tests
* fix: bump openapi doc with new grammar option
* fix: adjust test payload
* fix: bump test snaps
---------
Co-authored-by: Alex Weston <[email protected]>
* add prometheus port
* fix doc
* add port for trtllm and llamacpp
* Fixing format after rebase.
---------
Co-authored-by: Nicolas Patry <[email protected]>
* feat(gaudi): release ready (docs, docker image and vlm ready)
* fix(gaudi): add default argument for the dockerfile
* fix(gaudi): remove use of latest for gaudi docker image + redid gaudi benchmarking section to include best practices
* Fixing the tool calling convention.
* Update tehe doc.
* Fixing some corner cases.
* Fixing the tool call id.
* Fmt.
* Snapshot update with the new updated tool_call_id.
* More qwen2.
* Making `tool_calls` a vector.
* Update doc.
* Fixing the nix overlay with updated version.
* Add openai dependency.
* Updating the old tests.
* Trying to reduce the logs in the case of errors.
* Less spammy logs too.
* feat: add neuron backend
* feat(neuron): add server standalone installation
* feat(neuron): add server and integration tests
* fix(neuron): increase ulimit when building image
The base image used to compile the rust components seems to have a low
ulimit for opened files, which leads to errors during compilation.
* test(neuron): merge integration tests and fixtures
* test: add --neuron option
* review: do not use latest tag
* review: remove ureq pinned version
* review: --privileged should be the exception
* feat: add neuron case to build ci
* fix(neuron): export models from container in test fixtures
The neuron tests require models to have been previously exported and
cached on the hub. This is done automatically by the neuron.model
fixture the first time the tests are ran for a specific version.
This fixture used to export the models using optimum-neuron directly,
but this package is not necessarily present on the system.
Instead, it is now done through the neuron TGI itself, since it
contains all the tools required to export the models.
Note that since the CI runs docker in docker (dind) it does not seem
possible to share a volume between the CI container and the container
used to export the model.
For that reason, a specific image with a modified entrypoint is built
on-the-fly when a model export is required.
* refactor: remove sagemaker entry-point
The SageMaker image is built differently anyway.
* fix(neuron): avoid using Levenshtein
* test(neuron): use smaller llama model
* feat(neuron): avoid installing CUDA in image
* test(neuron): no error anymore when requesting too many tokens
* ci: doing a precompilation step (with a different token).
* test(neuron): avoid using image sha when exporting models
We now manually evaluate the apparent hash of the neuron backend by
combining the hash of the neuron backend directory and Dockerfile.
This new hash is used to identify exported neuron models instead of the
image sha.
This has two benefits:
- it changes less frequently (only hwen the neuron backend changes),
which means less neuron models being pushed to the hub,
- it can be evaluated locally, meaning that running the tests once
locally will export the models before the CI uses them.
* test(neuron): added a small script to prune test models
---------
Co-authored-by: drbh <[email protected]>
Co-authored-by: Nicolas Patry <[email protected]>
* make content field optional in chat request
* add tool_calls field to Message struct
* feat: add test and serialize tool messages
* fix: bump utopia, openapi doc version and improve test
* fix: rerun update docs
* fix: suppoer tool call id in template and remove unnecessary changes
* fix: ruff lint remove unused import
* fix: adjust message types in tests
---------
Co-authored-by: sailesh duddupudi <[email protected]>
The current code does not work and gives the following message:
UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style dictionaries with 'role' and 'content' keys.
warnings.warn(
Traceback (most recent call last):
File "/Users/angt/hf/tgi/test-gradio.py", line 22, in <module>
gr.ChatInterface(
TypeError: ChatInterface.__init__() got an unexpected keyword argument 'retry_btn'
Signed-off-by: Adrien Gallouët <[email protected]>
* feat: support qwen2.5 vl model
* fix: bump support models doc
* feat: check before rope type adjustment and small refactors
* fix: add transformer overlay for processor support
* fix: vendor processor and config from transformers
* fix: refactor/simplify conditionals
* Upgrade the version number.
* Remove modifications in Lock.
* Tmp branch to test transformers backend with 2.5.1 and TP>1
* Fixing the transformers backend.
inference_mode forces the use of `aten.matmul` instead of `aten.mm` the
former doesn't have sharding support crashing the transformers TP
support.
`lm_head.forward` also crashes because it skips the hook that
cast/decast the DTensor.
Torch 2.5.1 is required for sharding support.
* Put back the attention impl.
* Revert the flashinfer (this will fails).
* Building AOT.
* Using 2.5 kernels.
* Remove the archlist, it's defined in the docker anyway.
