text-generation-inference/server/text_generation_server
Nicolas Patry cb747b33da
Add deepseekv3 ()
* 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
..
adapters feat: improve star coder to support multi lora layers () 2025-01-16 16:23:55 -05:00
layers Add deepseekv3 () 2025-01-30 16:40:25 +01:00
models Add deepseekv3 () 2025-01-30 16:40:25 +01:00
pb chore: add pre-commit () 2024-02-16 11:58:58 +01:00
utils Add deepseekv3 () 2025-01-30 16:40:25 +01:00
__init__.py feat(clients): Python client () 2023-03-07 18:52:22 +01:00
cache.py fix(server): decrease memory fragmentation () 2023-07-06 14:28:33 +02:00
cli.py Fixing TRTLLM dockerfile. () 2025-01-20 11:13:46 +01:00
interceptor.py feat: prefill chunking () 2024-10-16 12:49:33 +02:00
server.py Tmp tp transformers () 2025-01-23 18:07:30 +01:00
tracing.py Add OTLP Service Name Environment Variable () 2024-06-25 09:33:01 +02:00