Pinned issues
Issues
- 7
- 4
kv_override issue with string values
#1487 opened by Erhan1706 - 0
Wrong switches: `unreachable-code-break` and `unreachable-code-return`, at least on Termux
#1494 opened by Manamama - 6
Can't install llama-cpp-python with HIPBLAS/ROCm on Windows
#1489 opened by mbamg - 1
- 2
Crashing with "IndexError: index 200 is out of bounds for axis 0 with size 200"
#1438 opened by phishmaster - 0
- 1
How should one accomplish plain topk sampling?
#1484 opened by brandon-lockaby - 3
"flash_attn = 0" is still still present on the newest llama-cpp-python versions
#1479 opened by BadisG - 0
Unable to make CMake find gcc and use CUDA Windows 11 CUDA tool kit installed 4gb video ram
#1485 opened by Vishwamithra37 - 0
cohere multilanguage aya model seem can not use response_format feature of llama-cpp-python
#1483 opened by svjack - 0
Issues with Llava-v1.6-34b and Llava16ChatHandler
#1482 opened by zenjieli - 0
install target fails for llava
#1481 opened by waheedi - 0
Please add response_format to create_completion
#1478 opened by dtkettler - 0
OS package system builds? (Apt, yum, etc)
#1480 opened by walterheck - 1
- 3
Unexpected output of embed
#1469 opened by shizidushu - 3
- 5
Add support for llava-1-5-phi3-mini
#1443 opened by CaptainOfHacks - 1
Add RPC backend support
#1455 opened by abetlen - 2
- 0
- 0
- 1
- 2
ValueError: could not broadcast input array from shape (371,) into shape (320,)
#1421 opened by utility-aagrawal - 0
MINGW / MSYS problem
#1464 opened by Zibri - 1
Segfault on load for embedding models lacking BOS/EOS token (such as `BAAI/bge-*`)
#1463 opened by iamlemec - 0
Support PyPI-installed `nvidia-cuda-runtime-cu12` and `nvidia-cublas-cu12`
#1460 opened by Interpause - 0
when depoly the llava-cpp-pyton server in k8s as a service , it can only answer questions about the first image
#1458 opened by adogwangwang - 0
- 2
GPU memory released for llava multimodal
#1451 opened by adogwangwang - 0
"split_mode=2 (row)" not working -- got Aborted
#1454 opened by oliverhh32 - 3
Severe Main Thread Bottleneck
#1452 opened by Beinsezii - 6
How to build the llamacpp's .so file separately and then pass it in the llama_cpp_python.
#1435 opened by fastdaima - 1
arm64 builds for CUDA
#1446 opened by mcvella - 1
- 0
- 2
Llama.generate: prefix-match hit is very slow.
#1437 opened by ndy200 - 0
CUDA Error : CUDA driver version is insufficient for CUDA runtime version
#1436 opened by VijayAsokkumar - 1
- 1
Add Nous Hermes 2 Pro function calling ChatHandler.
#1429 opened by stygmate - 1
Unable to install llama-cpp-python with CUBLAS or CUDA enabled under tensorflow-gpu docker image.
#1431 opened by brent-halen - 1
Which Python + CUDA version do you recommend for LLaVA on Windows 10 Pro 64-bit?
#1418 opened by Vinventive - 1
kv_override issue
#1417 opened by sudharshan1234 - 2
jinja2.exceptions.UndefinedError: 'dict object' has no attribute 'name' when running Functions.ipynb with Jupyter lab
#1405 opened by southkorea2013 - 0
Docker image
#1423 opened by Ravi-WingsBI - 1
GPU not recognized on CUDA 12.3
#1404 opened by y2ee201 - 1
cuda prebuilt wheel 12.3 error 404
#1406 opened by xandykati98 - 1
Multimodal Llama3 Support
#1403 opened by xx025 - 0