-
Notifications
You must be signed in to change notification settings - Fork 254
Issues: EricLBuehler/mistral.rs
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
UQFF File Not Generated When Using Metal Features
bug
Something isn't working
#810
opened Sep 30, 2024 by
solaoi
Llama 3.2 Vision 11B on Mac: Error "thread '<unnamed>' panicked at mistralrs-core/src/sampler.rs" while inferring image
bug
Something isn't working
models
Additions to model or architectures
triaged
This error has been reproduced or otherwise triaged.
#808
opened Sep 30, 2024 by
mathav95raj
Llama 3.2 on macOS: "Metal contiguous affine I64 not implemented"
bug
Something isn't working
triaged
This error has been reproduced or otherwise triaged.
#807
opened Sep 30, 2024 by
ChristianWeyer
Return finish_reason as an Enum - with wrapped stopping word/sequence/tok
new feature
New feature or request
#800
opened Sep 27, 2024 by
ShelbyJenkins
Add kernel support for AArch64 specific GGUF files, i.e. Q4_0_*_*
new feature
New feature or request
#799
opened Sep 27, 2024 by
smpurkis
Phi-3.5-vision-Instruct muliples images loading
new feature
New feature or request
#795
opened Sep 25, 2024 by
Aveline67
Additional math kernel support?
new feature
New feature or request
#794
opened Sep 25, 2024 by
dylanetaft
RequestMessage with tool_calls in Assistant message.
bug
Something isn't working
#793
opened Sep 25, 2024 by
Jeadie
404 error when loading Something isn't working
Phi3-small-8k-instruct
bug
#789
opened Sep 23, 2024 by
rlouf
CUDA_ERROR_ILLEGAL_ADDRESS when running Llama3 and Llama3.1
#783
opened Sep 20, 2024 by
ShelbyJenkins
How to deploy mistralrs on Android for large model inference?
new feature
New feature or request
#779
opened Sep 17, 2024 by
sopaco
Running in the MacBook M2 Pro Metal mode is too slow, and it becomes incredibly slow when the issue is slightly more complex.
bug
Something isn't working
#774
opened Sep 15, 2024 by
sopaco
metal phi3 --dtype bf16 "Function 'cast_f32_bf16' does not exist
bug
Something isn't working
#761
opened Sep 7, 2024 by
jk2K
CUDA out of memory with a presumed "full" offload to CPU
bug
Something isn't working
#751
opened Sep 4, 2024 by
av
blocking_recv hangs after first iteration in loop
bug
Something isn't working
#750
opened Sep 4, 2024 by
solaoi
Text generation: Implement beam search
new feature
New feature or request
#746
opened Sep 3, 2024 by
ChristianWeyer
Prebuilt binary for python bindings
new feature
New feature or request
#744
opened Sep 3, 2024 by
mert-kurttutan
Support for Gemma2 models in GGUF format
new feature
New feature or request
#722
opened Aug 28, 2024 by
solaoi
Enable multiple CPU from arguments
new feature
New feature or request
#680
opened Aug 13, 2024 by
lij55
Previous Next
ProTip!
Updated in the last three days: updated:>2024-09-29.