Skip to content

Issues: ModelCloud/GPTQModel

Beta
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 163 Closed
32 Open 163 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[BUG] RuntimeError: b_q_weight type is not kInt bug Something isn't working
#1625 opened Jun 2, 2025 by wumaotegan
2
Torch Linear instead of Triton Linear
#1617 opened May 20, 2025 by MekkCyber
How to Quantize LLaVA based models?
#1611 opened May 12, 2025 by Himanshunitrr
multi GPU setting
#1610 opened May 12, 2025 by chesterout
3
[BUG] AttributeError: "ProgressBar" object has no attribute 'set_postfix' bug Something isn't working
#1609 opened May 9, 2025 by mysterynan
mistral3
#1561 opened Apr 27, 2025 by ewof
1
8
Cannot Replicate Reported GSM8K-CoT Results from HF Model Using GPTQModel Codebase
#1560 opened Apr 25, 2025 by Eijnewgnaw
4
[BUG]TypeError: internvl_chat isn't supported yet. bug Something isn't working
#1556 opened Apr 23, 2025 by Maglanyulan
[Benchmark] Reproduce GPTQv2 results bug Something isn't working
#1545 opened Apr 16, 2025 by eldarkurtic
7
do we support QuaRot+GPTQv2 or SpinQuant+GPTQv2?
#1541 opened Apr 14, 2025 by coolKeen
1
Example script for quantization using QQQ
#1538 opened Apr 11, 2025 by DominikHil
GPTQModel with PEFT
#1534 opened Apr 11, 2025 by BUGBOY101
2
Sidestep NaN caused by div by zero where calculated scale == 0
#1529 opened Apr 10, 2025 by ywlq
12
[Question] Exllamv2 kernel may have accuracy issue for group_size 16 bug Something isn't working
#1515 opened Apr 8, 2025 by wenhuach21
2
[BUG] vllm support for QQQ format checkpoints bug Something isn't working
#1501 opened Apr 4, 2025 by jmkuebler
2
marlin g_idx issue when using dict devcie_map
#1499 opened Apr 3, 2025 by wenhuach21
2
[BUG] ValueError: Quantization: Failed due to NaN loss bug Something isn't working
#1497 opened Apr 2, 2025 by it-dainb
2
[BUG]cant install with torch-rocm bug Something isn't working
#1473 opened Mar 20, 2025 by yggdrasil75
7
[FEATURE] Sharded Quantization to Enable Consumer GPUs to Quantize 80B+ LLMs
#1468 opened Mar 18, 2025 by ColumbusAI
4
[Compat] Gemma 3 (VL) not supported: Only Gemma 3 text-only supported for now (1B) bug Something isn't working
#1465 opened Mar 16, 2025 by benjamin-marie
1
[FEATURE] ADD VPTQ
#1463 opened Mar 14, 2025 by Qubitium
3
[BUG] The dynamically quantized MoE model failed to deploy in vLLM. bug Something isn't working
#1455 opened Mar 13, 2025 by liweiqing1997
5
[BUG] RuntimeError: Numpy is not available bug Something isn't working
#1403 opened Mar 9, 2025 by davidray222
5
Can I quantize Qwen2-Audio-7B-Instruct using GPTQModel
#1375 opened Mar 4, 2025 by JeremyGe07
1
[KERNEL] AllSpark + Exllama vLLM
#1359 opened Mar 1, 2025 by Qubitium
ProTip! Find all open issues with in progress development work with linked:pr.