fakezeta 4a239a4bff feat(transformers): various enhancements to the transformers backend (#2468) ...

update transformers

*Handle Temperature = 0 as greedy search
*Handle custom works as stop words
*Implement KV cache
*Phi 3 no more requires trust_remote_code: true

2024-06-03 08:52:55 +02:00

..

cpp

deps(llama.cpp): update and adapt API changes (#2381)

2024-05-23 01:02:11 +02:00

go

feat(llama.cpp): do not specify backends to autoload and add llama.cpp variants (#2232)

2024-05-04 17:56:12 +02:00

python

feat(transformers): various enhancements to the transformers backend (#2468)

2024-06-03 08:52:55 +02:00

backend.proto

TTS API improvements (#2308)

2024-06-01 18:26:27 +00:00