Skip to content

Issues: IST-DASLab/marlin

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.

Sign up for GitHub

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

25 Open 4 Closed
25 Open 4 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Question about matrix A
#37 opened Oct 23, 2024 by Zhao-Dongyu
Marlin vs gguf
#36 opened Sep 13, 2024 by blap
1
comparison with FastTransformer for BatchSize=1
#35 opened Sep 11, 2024 by matrix97317
How to move the pointer of B and s in cuda kernel
#34 opened Aug 22, 2024 by Eutenacity
comparison with SmoothQuant
#32 opened Jul 29, 2024 by lxww302
1
RuntimeError: CUDA error: an illegal instruction was encountered when runing test.py
#30 opened Jul 2, 2024 by MekkCyber
2
Trying to understand the kernel
#29 opened Jun 27, 2024 by MekkCyber
Why the linear input for Layer.pack "must be of type torch.half"?
#28 opened Jun 26, 2024 by Azure-Tang
4
slight nondeterminism
#27 opened Jun 7, 2024 by MichoChan
2
perfmance
#26 opened May 7, 2024 by MichoChan
Issues to generate tokens after "get_llama_marlin"
#23 opened Apr 19, 2024 by HaoWuSR
a_sh_rd_delta_o
#22 opened Apr 12, 2024 by Lenan22
1
Marlin slower than fp16 on larger batches
#21 opened Apr 9, 2024 by mobicham
2
Questions about matrix A's layout in shared memory.
#20 opened Apr 8, 2024 by HandH1998
questions about slice_col_par
#19 opened Apr 7, 2024 by Lenan22
2
[QST] Weight Format & GEMM
#18 opened Apr 1, 2024 by jeromeku
2
groupsize=64 is not supported
#17 opened Mar 21, 2024 by jameswu2014
1
Do you have any plan support moe gemm?
#16 opened Mar 13, 2024 by LinHR000
Small typo in the shape description
#14 opened Feb 29, 2024 by saurabhdash
can this support lower bit quant?
#11 opened Jan 30, 2024 by vince62s
3
Where in the code uses "immediate eviction" and "fetched from L2 cache"??
#8 opened Jan 24, 2024 by ziyuhuang123
2
Support for Hopper H100
#7 opened Jan 22, 2024 by rosario-purple
3
[Bug] H800 run UT failed.
#6 opened Jan 22, 2024 by Ageliss
3
Does Marlin support zero-point quantization?
#5 opened Jan 20, 2024 by casper-hansen
7
Turing support
#4 opened Jan 20, 2024 by Dampfinchen
1
ProTip! What’s not been updated in a month: updated:<2024-11-28.