Mozilla-Ocho llamafile issues

Mozilla-Ocho / llamafile

Distribute and run LLMs with a single file.

https://llamafile.ai

Other

20.57k stars 1.04k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

add stable-diffusion.cpp to install target (fix #580)

#635 rgroesslinger opened 23 hours ago
0
Bug: Unable to integrate the completion endpoint with Cline [Error: type must be string, but is array]

#631 ocrumbs opened 6 days ago
2
Bug: Why llamafile don't remove end token like <|eot_id|> or <end_of_turn>?

#630 jeezrick opened 1 week ago
0
Feature Request: Support AVX-512 for Intel Rocket Lake

#628 aluklon opened 1 week ago
0
تسليك المجاري بالضغط

#627 sewerageservices closed 1 week ago
0
معالجة الروائح الكريهة

#626 sewerageservices closed 1 week ago
0
خدمة تنظيف بالوعات

#625 sewerageservices closed 1 week ago
0
شفط مجاري الصرف الصحي

#624 sewerageservices closed 1 week ago
0
خدمة صرف الصحي

#623 sewerageservices closed 1 week ago
0
تنظيف البيارات

#622 sewerageservices closed 1 week ago
0
شركة النهر لخدمات العوازل

#621 sewerageservices closed 1 week ago
0
شركة كشف تسربات المياه

#620 sewerageservices closed 1 week ago
0
شركة تسليك مجاري في الشارقة

#619 sewerageservices closed 1 week ago
0
شركة تسليك مجاري في راس الخيمة

#618 sewerageservices closed 1 week ago
0
النهر لخدمات الصرف الصحي في الامارات

#617 sewerageservices closed 1 week ago
0
شركة تسليك مجاري في دبي

#616 sewerageservices closed 1 week ago
0
Bug: Cannot use llama 3.2 vision

#615 GeorgelPreput closed 6 days ago
3
Add kitops as a way to run llamafile

#613 gorkem opened 1 week ago
0
Bug: Shared memory not working, results in Segfault

#611 abishekmuthian opened 2 weeks ago
1
Bug: segfault loading models with KV quantization and related problems

#610 mseri opened 2 weeks ago
0
Bug: GPU Acceleration works for one but not the other users on same Linux machine

#609 lovenemesis opened 2 weeks ago
0
Granite three support

#608 gabe-l-hart opened 2 weeks ago
4
[llamafiler] doc/v1_chat_completions.md: remove duplicate entry

#607 mseri opened 2 weeks ago
0
Support for configurable URL prefix in llamafiler

#604 vlasky closed 3 weeks ago
1
Bug: imatrix quant gguf models (e.g. IQ3_XS, IQ2_M) not using NV GPU properly with `llamafile-0.8.14`

#603 wingenlit closed 3 weeks ago
1
Bug: 'cmath' file not found on Windows with AMD Dedicated GPU

#601 DK013 opened 4 weeks ago
0
Feature Request: CORS fallback for OpenAI API compatible endpoints

#600 DK013 opened 4 weeks ago
0
Bug: Whisperfile: can't turn off translation

#599 hheexx opened 4 weeks ago
2
Bug: Can't load Llama-3.2-3B-Instruct-f16, i.e. full weights without quantization on CUDA (GTX1070)

#598 SergeyDidenko closed 4 weeks ago
3
Support for configurable URL prefix when running in server mode

#597 vlasky closed 1 month ago
0
feat: setup script for llamafile

#593 hemanth opened 1 month ago
3
Bug: mlock is failing and llama-server is outdated for very long time.

#591 BoQsc closed 1 month ago
3
Bug: llamafiler /v1/embeddings endpoint does not return model name

#589 wirthual opened 1 month ago
0
Bug: `--path` Option Broken When Pointing to a Folder

#588 gorkem opened 1 month ago
0
Bug: binary called ape in PATH breaks everything

#587 step21 opened 1 month ago
0
add llama_matmul_demo2_bf16.c with other parallelize experiment

#586 Djip007 opened 1 month ago
2
Update WSL troubleshooting in README.md

#585 halter73 opened 1 month ago
0
Bug: Phi3.5-mini-instruct Q4 K L gguf based llamafile CuDA error AMD iGPU

#584 eddan168 opened 1 month ago
0
Feature Request: /v1/models endpoint for further openai api compatibility

#583 quantumalchemy opened 1 month ago
1
Bug: unknown argument --rope-scale

#582 charleswg opened 1 month ago
1
Enable GPU support in llama-bench

#581 cjpais closed 1 month ago
0
Bug: install: cannot stat 'o/x86_64/stable-diffusion.cpp/main': No such file or directory

#580 toby3d opened 1 month ago
0
Bug: APE is running on WIN32 inside WSL - whisperfile - zsh

#579 baptistecs opened 1 month ago
1
Bug: Huge difference between prompt processing (tokens/sec) compared to Llama cpp or Ollama

#577 mathav95raj closed 1 month ago
7
Google

#576 istprivatsache closed 1 month ago
0
Update README: Add llama 3.2 to model table

#575 wirthual closed 2 weeks ago
2
/embedding API

#571 invisiblepancake opened 1 month ago
0
No additional speed up after installing oneMKL

#570 invisiblepancake opened 1 month ago
0
(For "history": bench with llamafile V0.8.6)

#569 invisiblepancake opened 1 month ago
0
whisperfile server: convert files without ffmpeg

#568 cjpais closed 1 month ago
0