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
Insitu quantization OOM for large models
bug
Something isn't working
#344
opened May 23, 2024 by
nidhoggr-nil
Python mistralrs-cuda not running on GPU
bug
Something isn't working
#342
opened May 22, 2024 by
joshpopelka20
Garbled output on very long prompts
bug
Something isn't working
urgent
#339
opened May 21, 2024 by
LLukas22
Benching local GGUF model layers allocated to vRAM but no GPU activity
bug
Something isn't working
#330
opened May 19, 2024 by
polarathene
bug: If device layers requested exceed model layers, host layers overflow
bug
Something isn't working
resolved
#329
opened May 19, 2024 by
polarathene
Running model from a GGUF file, only
bug
Something isn't working
#326
opened May 17, 2024 by
MoonRide303
mistral does not support NVIDIA V100 (compute_cap <= 800)
bug
Something isn't working
#305
opened May 14, 2024 by
thesues
Quantized Phi3: Features to add
models
Additions to model or architectures
#277
opened May 9, 2024 by
EricLBuehler
1 of 2 tasks
LoRA swapping at runtime
models
Additions to model or architectures
new feature
New feature or request
#259
opened May 1, 2024 by
BHX2
Add C api and provide shared and static libraries.
new feature
New feature or request
#258
opened May 1, 2024 by
maximus2600
Batched & chunked prefill
models
Additions to model or architectures
new feature
New feature or request
#216
opened Apr 26, 2024 by
lucasavila00
Model Wishlist
models
Additions to model or architectures
#156
opened Apr 16, 2024 by
EricLBuehler
10 tasks
Need parallel linears
backend
Backend work
paged-attention
#50
opened Apr 1, 2024 by
EricLBuehler
3 tasks
Add topk scalings, topk softmax scalings for X-LoRA
models
Additions to model or architectures
new feature
New feature or request
#48
opened Mar 30, 2024 by
EricLBuehler
ProTip!
Updated in the last three days: updated:>2024-05-20.