text-generation-inference/server/text_generation_server
Daniël de Kok e32528792c
Switch to punica-sgmv kernel from the Hub ()
* Switch to punica-sgmv kernel from the Hub

This also switches (temporarily) to the tgi-nix/kernel-builder merge
branch, bumping up to CUDA 12.8 (same as non-Nix Torch).

* nix: client depends on aiohttp

This probably worked before the nixpkgs bump because a dependency
propagated aiohttp.
2025-05-21 15:44:15 +02:00
..
adapters Switch to punica-sgmv kernel from the Hub () 2025-05-21 15:44:15 +02:00
layers Switch to punica-sgmv kernel from the Hub () 2025-05-21 15:44:15 +02:00
models Chunked Prefill VLM () 2025-05-06 18:01:59 +02:00
pb chore: add pre-commit () 2024-02-16 11:58:58 +01:00
utils Switch to punica-sgmv kernel from the Hub () 2025-05-21 15:44:15 +02:00
__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 Chunked Prefill VLM () 2025-05-06 18:01:59 +02:00
tracing.py Add OTLP Service Name Environment Variable () 2024-06-25 09:33:01 +02:00