text-generation-inference/backends/neuron/server
David Corvoysier 787e28bf59 fix(generator): emulate greedy in sampling parameters
When on-device sampling is enabled, we need to emulate the greedy
behaviour using top-k=1, top-p=1, temperature=1.
2025-06-06 15:31:05 +00:00
..
text_generation_server fix(generator): emulate greedy in sampling parameters 2025-06-06 15:31:05 +00:00
.gitignore Add Neuron backend (#3033) 2025-02-24 09:10:05 +01:00
build-requirements.txt Add Neuron backend (#3033) 2025-02-24 09:10:05 +01:00
Makefile Add Neuron backend (#3033) 2025-02-24 09:10:05 +01:00
pyproject.toml setuptools <= 70.0 is vulnerable: CVE-2024-6345 (#3171) 2025-04-15 10:09:37 +02:00