Skip to content

Pull requests: AutoGPTQ/AutoGPTQ

New pull request New
31 Open 205 Closed
31 Open 205 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix transformers 4.38.0 seq_len
#668 opened May 11, 2024 by randoentity Loading…
1
[FEATURE] Support BitBLAS Backend for QuantLinear
#662 opened May 1, 2024 by LeiWang1999 Loading…
3
Support QBits kernel for CPU device
#660 opened Apr 29, 2024 by PenghuiCheng Loading…
2
[BUG/DEPRECATION] Remove fused attention/mlp
#659 opened Apr 28, 2024 by Qubitium Loading…
4 tasks done
2
[DEPRECATION] Remove triton v1
#658 opened Apr 28, 2024 by Qubitium Loading…
4 tasks done
[USABILITY] Warn users if quantization using insufficient nsamples
#656 opened Apr 28, 2024 by Qubitium Loading…
[BUG] Fix H100 crash/compat with Marlin
#654 opened Apr 27, 2024 by Qubitium Loading…
3 tasks done
1
Extend support for Phi-3 models
#651 opened Apr 27, 2024 by davidgxue Loading…
1
3
[FEATURE] Allow loading of quantized lm_head
#648 opened Apr 25, 2024 by Qubitium Loading…
1 task done
1
8
Save sharded checkpoints
#645 opened Apr 19, 2024 by LaaZa Loading…
[PERFORMANCE] Fix Packing thread regression in code
#642 opened Apr 16, 2024 by Qubitium Loading…
2 tasks done
1
[BUG/FEATURE] Fix Sym=False, new checkpoint_format = gptq_v2
#640 opened Apr 12, 2024 by Qubitium Loading…
29 tasks done
73
[SYCL] Intel SYCL runtime support for AutoGPTQ
#638 opened Apr 11, 2024 by abhilash1910 • Draft
2
[WIP] [WORKING] dbrx (mod) support
#625 opened Mar 29, 2024 by Qubitium • Draft
46
Add support for DBRX
#623 opened Mar 28, 2024 by LaaZa • Draft
1
8
Add support for InternLM-XComposer2-VL
#619 opened Mar 27, 2024 by LaaZa Loading…
1
Add Qwen2MoE
#593 opened Mar 14, 2024 by bozheng-hit Loading…
11
Format logging output in a form of a table
#569 opened Feb 28, 2024 by Andrei-Aksionov Loading…
Fix for fields being lists
#563 opened Feb 23, 2024 by stevelaskaridis Loading…
5
Support CPU only quantization.
#558 opened Feb 20, 2024 by miaojinc Loading…
[Minor] peft bug fix: HF peft version and tokenizer path in peft scripts
#493 opened Dec 24, 2023 by realAsma Loading…
1
Fix unnessary vram usage while injecting fused attn
#453 opened Nov 28, 2023 by lszxb Loading…
5
Allow specifying GPU used for quantisation, overriding hardcoded cuda:0
#405 opened Nov 5, 2023 by TheBloke Loading…
3
Save and Load sharded gptq checkpoint
#364 opened Oct 7, 2023 by PanQiWei Loading…
6
Fix g_idx in fused kernel
#305 opened Aug 30, 2023 by chu-tianxiang Loading…
ProTip! Add no:assignee to see everything that’s not assigned.