text-generation-inference/docs/source
Nicolas Patry cb747b33da
Add deepseekv3 (#2968)
* Add fp8 support moe models

add deepseekv3

format codfe'

update dockerfile

update doc

* Small modifications.

* Moe kernels 0.8.1

* Upgrade to 0.8.1

* Fixing moe import.

* Black.

* Apply suggestions from code review

Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com>

* Fixing Mixtral + Nits.

* Put link to ref.

* Fix other call locations.

* Scoring func `softmax` is the only one that works.

---------

Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com>
2025-01-30 16:40:25 +01:00
..
backends fix: lint backend and doc files (#2850) 2024-12-16 16:12:34 -05:00
basic_tutorials Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
conceptual Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
reference Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
_toctree.yml Fix typo in TPU docs (#2911) 2025-01-15 18:32:07 +01:00
architecture.md TensorRT-LLM backend bump to latest version + misc fixes (#2791) 2024-12-13 15:50:59 +01:00
index.md Removing ../ that broke the link (#2789) 2024-12-02 05:48:55 +01:00
installation_amd.md Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
installation_gaudi.md MI300 compatibility (#1764) 2024-05-17 15:30:47 +02:00
installation_inferentia.md MI300 compatibility (#1764) 2024-05-17 15:30:47 +02:00
installation_intel.md Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
installation_nvidia.md Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
installation_tpu.md Fix typo in TPU docs (#2911) 2025-01-15 18:32:07 +01:00
installation.md MI300 compatibility (#1764) 2024-05-17 15:30:47 +02:00
multi_backend_support.md fix: lint backend and doc files (#2850) 2024-12-16 16:12:34 -05:00
quicktour.md Tmp tp transformers (#2942) 2025-01-23 18:07:30 +01:00
supported_models.md Add deepseekv3 (#2968) 2025-01-30 16:40:25 +01:00
usage_statistics.md fix: Telemetry (#2957) 2025-01-28 10:29:18 +01:00