text-generation-inference/backends
Alvaro Moran 8801ba12cf
Optimum neuron 0.3.0 (#3308)
* chore(neuron): update to optimum-neuron 0.3.0

Dependencies were changed accordingly, because Neuron SDK was updated to
v2.24.

* test: sample is not deterministic

Also modify the temperature in decode test to avoid granite early
stopping.

* test(neuron): adjust expectations after graph changes

* test(neuron): use greedy for stop sequences

---------

Co-authored-by: David Corvoysier <david@huggingface.co>
2025-08-26 11:07:47 +02:00
..
client Revert "feat: improve qwen2-vl startup " (#2924) 2025-01-17 12:09:05 -05:00
gaudi Gaudi gptq gidx support (#3297) 2025-07-17 16:00:12 +02:00
grpc-metadata Upgrading our rustc version. (#2908) 2025-01-15 17:04:03 +01:00
llamacpp Add option to configure prometheus port (#3187) 2025-04-23 20:43:25 +05:30
neuron Optimum neuron 0.3.0 (#3308) 2025-08-26 11:07:47 +02:00
trtllm Add option to configure prometheus port (#3187) 2025-04-23 20:43:25 +05:30
v2 Add option to configure prometheus port (#3187) 2025-04-23 20:43:25 +05:30
v3 fp8 compressed tensors w8a8 support for Gaudi backend (#3242) 2025-05-28 14:54:20 +02:00