Skip to content

Issues: mit-han-lab/deepcompressor

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

22 Open 7 Closed
22 Open 7 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

OOM when use deepcompressor quantize llama2 w4a8 per-group with H100 80G
#33 opened Dec 3, 2024 by Andy0422
error in trt_llm conversion
#32 opened Dec 3, 2024 by Andy0422
use qserve with tensorrt-llm raise an error
#31 opened Nov 27, 2024 by anaivebird
2 of 4 tasks
1
torch.OutOfMemoryError: CUDA out of memory
#30 opened Nov 26, 2024 by Lenan22
AttributeError: 'tuple' object has no attribute 'shape'
#29 opened Nov 26, 2024 by Lenan22
AttributeError: 'NoneType' object has no attribute 'name'
#28 opened Nov 25, 2024 by Lenan22
2
Quantized custom flux model was still bfloat16
#27 opened Nov 20, 2024 by samedii
5
How to apply SVDQuant for SD3 model?
#26 opened Nov 14, 2024 by wxsms
Quantization of Other Models
#25 opened Nov 12, 2024 by Oguzhanercan
Question about quantize time for custom flux transformer
#24 opened Nov 12, 2024 by chuck-ma
5
What is the function 'patch_attention' for?
#20 opened Oct 11, 2024 by mxjmtxrm
1
support for W4A8KV8/16 and other models
#19 opened Sep 30, 2024 by KKwanhee
2
will you support quantize the embedding layer and lm_head layer?
#18 opened Sep 6, 2024 by geqian-9192
2
[Bug] RuntimeError: Boolean value of Tensor with more than one value is ambiguous
#17 opened Aug 10, 2024 by ChenMnZ
3
GPTQ LLAMA 2 7B Question
#16 opened Aug 8, 2024 by XiaohanFei
1
Why Rotate Again in main.py
#15 opened Jul 30, 2024 by RanchiZhao
3
MLA supported
#14 opened Jul 17, 2024 by RanchiZhao
Group shape error
#13 opened Jul 5, 2024 by LuckyLYM
1
Questions about rotation
#12 opened Jun 28, 2024 by Kyeong-Joong
1
Unable to reproduce RTN results in paper
#8 opened Jun 7, 2024 by Golden-Wang
1
QoQ-g128 Llama3-70B-Instruct Results
#7 opened Jun 3, 2024 by ethxnp
AssertionError: The smooth scale contains NaN.
#5 opened Jun 3, 2024 by ethxnp
1
ProTip! Find all open issues with in progress development work with linked:pr.