Issues
state:open label:bug
state:open label:bug
Search results
<code>Llama.embed</code> crashes when <code>n_batch</code> > 512
bugSomething isn't workingSomething isn't workingStatus: Open.#1762 In abetlen/llama-cpp-python;No matter how many times I build it, it won't start
bugSomething isn't workingSomething isn't workingStatus: Open.#1719 In abetlen/llama-cpp-python;flash attention on Nvidia Tesla P100s results in the <code>CUDA error: unspecified launch failure</code> - (<code>CUDA kernel flash_attn_tile_ext_f16 has no device code compatible with CUDA arch 520</code>)
bugSomething isn't workingSomething isn't workingStatus: Open.#1710 In abetlen/llama-cpp-python;Problem with v0.2.88
bugSomething isn't workingSomething isn't workingStatus: Open.#1684 In abetlen/llama-cpp-python;High CPU Usage, very slow performance, with flash_attn=true on ROCM 6.1.2
bugSomething isn't workingSomething isn't workingStatus: Open.#1661 In abetlen/llama-cpp-python;Error When Loading Model with llama_cpp: [WinError -1073741795] Windows Error 0xc000001d
bugSomething isn't workingSomething isn't workingStatus: Open.#1660 In abetlen/llama-cpp-python;pip install llama-cpp-python on anaconda
bugSomething isn't workingSomething isn't workingStatus: Open.#1654 In abetlen/llama-cpp-python;Installing the pre-built v0.2.85 – v0.3.0 Metal wheels for Python 3.9 – 3.12 yields <code>Bad magic number for file header</code>
bugSomething isn't workingSomething isn't workingStatus: Open.#1650 In abetlen/llama-cpp-python;create_chat_completion is stuck in versions 0.2.84 and 0.2.85 for Mac Silicon
bugSomething isn't workingSomething isn't workingStatus: Open.#1648 In abetlen/llama-cpp-python;All requests end with 'finish_reason': 'length' when the max_tokens=-1 parameter is set.
bugSomething isn't workingSomething isn't workingStatus: Open.#1645 In abetlen/llama-cpp-python;Pre-built cpu wheel does not work on Ubuntu due to libc.musl dependency
bugSomething isn't workingSomething isn't workingStatus: Open.#1628 In abetlen/llama-cpp-python;CUDA error: unspecified launch failure on inference on Nvidia V100 GPUs
bugSomething isn't workingSomething isn't workingStatus: Open.#1624 In abetlen/llama-cpp-python;