Issues
- 3
RWKV support (sync llama.cpp)
#77 opened by tomasmcm - 3
cannot load model
#49 opened by loekTheDreamer - 1
- 1
Unable to import model
#76 opened by Prasad-178 - 1
- 1
Continuous Batching
#70 opened by Meowmix42069 - 1
Crash on both IOS and Android when using embeddings
#62 opened by okwes - 2
Crash on loading specifc model
#57 opened by Vali-98 - 2
Sync llamacpp again
#63 opened by GameOverFlowChart - 0
- 2
- 2
llama.rn crashes when proguard is enabled
#59 opened by Vali-98 - 2
Implementing optimizations from layla
#50 opened by Vali-98 - 2
Feature Request: TextStreaming
#46 opened by hushaudio - 1
- 0
Bump llamacpp version pls
#53 opened by GameOverFlowChart - 4
Update llamacpp module to latest
#44 opened by Vali-98 - 1
LLaVa support
#33 opened by jhen0409 - 4
OpenCL Implementation for Android
#40 opened by Vali-98 - 6
stablelm-2-zephyr-1_6b-Q8_0.gguf does not work
#43 opened by batrlatom - 3
Failure to initLlama on Xiaomi phones.
#42 opened by Vali-98 - 0
- 1
Seed, min p
#39 opened by Ar57m - 3
- 0
Benchmark method
#8 opened by jhen0409 - 0
Parallel decoding
#30 opened by jhen0409 - 1
Early stopping inference
#24 opened by JEF1056 - 0
Prompt cache
#14 opened by jhen0409 - 0
Support Android
#5 opened by jhen0409 - 1
- 0
Example: Pure text completion playground
#2 opened by jhen0409 - 0
Example: Custom params in the UI
#3 opened by jhen0409