issues Search Results · repo:Mozilla-Ocho/llamafile language:C++

Filter by

• • Code... (...)results
  • Issues474 (474)results
  • Pull requests116 (116)results
  • Discussions93 (93)results
  • Commits0 (0)results
  • Packages0 (0)results
  • Wikis0 (0)results

• State

  • Open
  • Closed

• Advanced

  • Owner
  • State
  • Close reason
  • Has linked pull request
  • Author
  • Assignee
  • Mentioned user
  • Mentioned team
  • Commenter
  • Involved user
  • Label
  • Milestone
  • Number of comments
  • Number of interactions
• Advanced search

Issues474 (474)

474 results

 (71 ms)

474 results

inMozilla-Ocho/llamafile (press backspace or delete to remove)

Sort by: Best match

Filter

Mozilla-Ocho/llamafile

Bug: Can not compile `iqk_mul_mat_arm82.cpp` from in ubuntu20.04 aarch64 NEON error: inlining failed in call to always_inline ‘float16x4_t vmul_f16(float16x4_t, float16x4_t)’: target specific option mismatch

Contact Details tridu33@qq.com What happened? download and compile in Ubuntu20.04, aarch64 #!/bin/bash /usr/bin/g++ -Dcpuinfer_ext_EXPORTS -march=armv8-a \ -I/home/tridu33/ktransformers/ktransformers_ext/../../third_party ...

bug

critical severity

• Tridu33
·
• 7
·
• Opened 
  5 days ago
·
• #706

Mozilla-Ocho/llamafile

Bug: whisperfile documentation doesn't mention server option

Contact Details No response What happened? A couple of weeks ago I was looking for a similar option as llamafile server for whisperfile but I couldn t find it in the whisperfile documentation. Then ...

bug

low severity

• alonsosilvaallende
·
• 1
·
• Opened 
  7 days ago
·
• #704

Mozilla-Ocho/llamafile

Bug: Segmentation Fault with CUDA Initialization on Whisperfile server

Contact Details No response What happened? When I run the whisperfile server: ./whisperfile-0.9.0 -m ggml-tiny.en.bin --gpu nvidia and then on another terminal: curl 127.0.0.1:8080/inference -H ...

bug

high severity

• alonsosilvaallende
·
• 1
·
• Opened 
  8 days ago
·
• #703

Mozilla-Ocho/llamafile

Bug: failed to start in embedding mode

What happened? ./Llama-3.2-1B-Instruct.Q6_K.llamafile --server --embedding --nobrowser error: unknown argument: --nobrowser Without passing --nobrowser /Llama-3.2-1B-Instruct.Q6_K.llamafile --server ...

bug

critical severity

• harikt
·
• 1
·
• Opened 
  8 days ago
·
• #702

Mozilla-Ocho/llamafile

Bug: max_completion_tokens being ignored

Contact Details nathan@mozilla.ai What happened? I m using LiteLLM to inference Llamafile in Lumigator (https://github.com/mozilla-ai/lumigator/blob/main/lumigator/jobs/inference/model_clients.py#L65) ...

bug

medium severity

• njbrake
·
• Opened 
  9 days ago
·
• #701

Mozilla-Ocho/llamafile

Little help please

Hi guys, I m trying to run this $ llamafile -m qwen2.5-coder-7b-instruct-q8_0.gguf --gpu NVIDIA █...╝ launching server... error: Uncaught SIGSEGV (SEGV_MAPERR) at 0x328 on legion pid 249503 tid 249511 ...

• betim
·
• 1
·
• Opened 
  11 days ago
·
• #700

Mozilla-Ocho/llamafile

Bug: error loading model DeepSeek-R1-Q4_K_M.gguf : error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-v3'

Contact Details tridu33@qq.com What happened? i download GGUF files DeepSeek-R1-Q4_K_M from https://www.modelscope.cn/models/unsloth/DeepSeek-R1-GGUF/files , merge them into one single file: /home/tridu33/workspace/llama.cpp4Ascend/build/bin/llama-gguf-split ...

bug

critical severity

• Tridu33
·
• 4
·
• Opened 
  12 days ago
·
• #699

Mozilla-Ocho/llamafile

Bug: llamafile won't load user defined system prompt file

Contact Details stonez56@gmail.com What happened? I would like to include my own system prompt file when start the Llamafile. I have tried: -spf FNAME --system-prompt-file FNAME both won t work. How ...

bug

low severity

• stonez56
·
• Opened 
  19 days ago
·
• #698

Mozilla-Ocho/llamafile

Bug: `error: unknown argument: --lora`

Contact Details No response What happened? I can t use the --lora parameter. I expected it to work, but maybe I’m specifying the parameters wrong. Has anyone experienced this issue? Version llamafile ...

bug

high severity

• michaelact
·
• 1
·
• Opened 
  19 days ago
·
• #697

Mozilla-Ocho/llamafile

Bug: Segmentation Fault during CUDA Initialization with GPU Offloading Enabled

Contact Details No response What happened? Segmentation Fault during CUDA Initialization with GPU Offloading Enabled Description: When running the binary with GPU offloading enabled (e.g., using -ngl ...

bug

critical severity

• FordUniver
·
• 5
·
• Opened 
  20 days ago
·
• #696

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues

ProTip! 

Restrict your search to the title by using the in:title qualifier.

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues

ProTip! 

Press the

/

key to activate the search input again and adjust your query.