Skip to content

Issues: vllm-project/llm-compressor

MODEL REQUESTS
#69 opened Aug 8, 2024 by robertgshaw2-neuralmagic
Open 63
Q3 ROADMAP
#30 opened Jul 22, 2024 by robertgshaw2-neuralmagic
Open 4
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

32 Open 61 Closed
32 Open 61 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

CUDA OOM while saving compressed Llama-3.1-70b with AutoModelForCausalLM bug Something isn't working
#928 opened Nov 20, 2024 by hibukipanim
@horheynm
6
Got Error when I load a 2of4 model using vllm. bug Something isn't working
#926 opened Nov 19, 2024 by jiangjiadi
@dsikka
13
Encounter error "No modifier of type 'SparseGPTModifier' found" when upgrading to 0.3.0 bug Something isn't working
#925 opened Nov 19, 2024 by jiangjiadi
@dsikka
1
Discuss the use of hyperparameters in the quantization_w8a8_int8 script documentation Improvements or additions to documentation
#916 opened Nov 14, 2024 by HelloCard
@kylesayrs
10
Finetuning in 2:4 sparsity w4a16 example fails with multiple GPUs bug Something isn't working
#911 opened Nov 13, 2024 by arunpatala
2
W8A8 quant for GPT-J failed bug Something isn't working
#909 opened Nov 12, 2024 by zhouyuan
2
Can we quantize Qwen/Qwen2.5-Math-RM-72B?
#900 opened Nov 7, 2024 by yechenzhi
Only one GPU shows usage while quantizing
#890 opened Nov 3, 2024 by gmonair
@dsikka
4
[Usage] How to manually set calibration_function?
#886 opened Nov 1, 2024 by donpromax
@rahul-tuli
1
OOM, deepseek v2 code lite on A40 gpus bug Something isn't working
#885 opened Nov 1, 2024 by tohnee
@dsikka
2
Any plan about W4A8 enhancement New feature or request
#873 opened Oct 29, 2024 by Arcmoon-Hu
1
Model saving fails on AWS instances with OOM kill bug Something isn't working
#868 opened Oct 25, 2024 by Arseny-N
Output of Compressor unable to be to be loaded by latest HF Transformers bug Something isn't working
#865 opened Oct 23, 2024 by hyaticua
@dsikka
2
Does llm-compressor support minicpm3 which is MLA architecture？ enhancement New feature or request
#860 opened Oct 22, 2024 by piamo
@kylesayrs
2
Is it possible to quantize to FP8 W8A16 without calibration data enhancement New feature or request
#858 opened Oct 21, 2024 by us58
1
Perplexity (ppl) Calculation of Local Sparse Model: NaN issue bug Something isn't working
#853 opened Oct 19, 2024 by HengJayWang
2
Why is the speed does not increase after compressed it? bug Something isn't working
#852 opened Oct 18, 2024 by liho00
8
[Question]Does Minicpmv2.6 currently support int8/fp8 quantization?
#848 opened Oct 15, 2024 by wjj19950828
3
AttributeError: 'CompressedLinear' object has no attribute 'weight' bug Something isn't working
#835 opened Oct 9, 2024 by kylesayrs
@kylesayrs
When to support multi-nodes quantization? enhancement New feature or request
#831 opened Oct 9, 2024 by IEI-mjx
@markurtz
2
No model size reduction seen
#790 opened Oct 5, 2024 by sriyachakravarthy
@markurtz
2
AttributeError: 'MllamaConfig' object has no attribute 'use_cache' bug Something isn't working
#688 opened Sep 26, 2024 by mgoin
1
@kylesayrs
SmoothQuant doesn't respect ignored modules for VLMs bug Something isn't working
#687 opened Sep 26, 2024 by mgoin
2
KV Cache Quantization example cause problem bug Something isn't working
#660 opened Sep 25, 2024 by weicheng59
@markurtz
3
[USAGE] FP8 W8A8 (+KV) with LORA Adapters enhancement New feature or request
#164 opened Sep 11, 2024 by paulliwog
@markurtz
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.