snapshot-2024-04-28

What's Changed

• Bumped ExLlamaV2 to version 0.0.19 to resolve #5851 by @ashleykleynhans in #5880
• Bump llama-cpp-python to 0.2.64, use official wheels by @oobabooga in #5921
• nvidia docker: make sure gradio listens on 0.0.0.0 by @jvanmelckebeke in #5918
• Revert walrus operator for params['max_memory'] by @Column01 in #5878
• Merge dev branch by @oobabooga in #5927

New Contributors

• @jvanmelckebeke made their first contribution in #5918
• @Column01 made their first contribution in #5878

Full Changelog: snapshot-2024-04-21...snapshot-2024-04-28

snapshot-2024-04-21

What's Changed

• Fix whisper STT by @mamei16 in #5856
• [Hotfix] Revert sse-starlette version bump because it breaks API request cancellation by @p-e-w in #5873
• Add a /v1/internal/chat-prompt endpoint by @oobabooga in #5879
• Merge dev branch by @oobabooga in #5887

New Contributors

• @p-e-w made their first contribution in #5873

Full Changelog: snapshot-2024-04-14...snapshot-2024-04-21

snapshot-2024-04-14

What's Changed

• Add a simple min_p preset, make it the default by @oobabooga in #5836
• Respect model and lora directory settings when downloading files by @acon96 in #5842
• FIX Issue #5783 Transparency to image cache by @Victorivus in #5827
• Update gradio requirement from ==4.25.* to ==4.26.* by @dependabot in #5832
• Fix saving of UI defaults to settings.yaml - Fixes #5592 by @ashleykleynhans in #5794
• Take HF_ENDPOINT in consideration by @zaypen in #5571
• Add Ascend NPU support by @wangshuai09 in #5541
• Bump sse-starlette from 1.6.5 to 2.1.0 by @dependabot in #5831
• Merge dev branch by @oobabooga in #5848

New Contributors

• @acon96 made their first contribution in #5842
• @Victorivus made their first contribution in #5827
• @wangshuai09 made their first contribution in #5541

Full Changelog: snapshot-2024-04-07...snapshot-2024-04-14

snapshot-2024-04-07

What's Changed

• Remove CTransformers support by @oobabooga in #5807
• Merge dev branch by @oobabooga in #5810
• Bump aqlm[cpu,gpu] from 1.1.2 to 1.1.3 by @dependabot in #5790
• Merge dev branch by @oobabooga in #5822
• requirements: add psutil by @cebtenzzre in #5819
• Merge dev branch by @oobabooga in #5823

Full Changelog: snapshot-2024-03-31...snapshot-2024-04-07

snapshot-2024-03-31

What's Changed

• Bump gradio to 4.23 by @oobabooga in #5758
• Fix prompt incorrectly set to empty when suffix is empty string by @Yiximail in #5757
• Set an default empty string for user_bio to fix #5717 issue. by @Yiximail in #5722
• docker: Remove misleading CLI_ARGS by @wldhx in #5726
• Add config for hyperion and hercules models to use chatml by @bartowski1182 in #5742
• Bump aqlm[cpu,gpu] from 1.1.0 to 1.1.2 by @dependabot in #5728
• Organize the parameters tab by @oobabooga in #5767
• Merge dev branch by @oobabooga in #5772

New Contributors

• @wldhx made their first contribution in #5726

Full Changelog: snapshot-2024-03-24...snapshot-2024-03-31

snapshot-2024-03-24

Full Changelog: snapshot-2024-03-17...snapshot-2024-03-24

snapshot-2024-03-17

What's Changed

• Make superbooga & superboogav2 functional again by @oobabooga in #5656
• Add AQLM support (experimental) by @oobabooga in #5466
• Bump AutoAWQ to 0.2.3 (Linux only) by @oobabooga in #5658
• Add StreamingLLM for llamacpp & llamacpp_HF (2nd attempt) by @oobabooga in #5669
• Merge dev branch by @oobabooga in #5680
• UI: Add a new "User description" field for user personality/biography by @oobabooga in #5691
• Merge dev branch by @oobabooga in #5716

Full Changelog: snapshot-2024-03-10...snapshot-2024-03-17

snapshot-2024-03-10

What's Changed

• Update PyTorch to 2.2 (also update flash-attn to 2.5.6) by @oobabooga in #5618
• Do not install extensions requirements by default by @oobabooga in #5621
• Create an update wizard by @oobabooga in #5623
• Gradio 4 by @oobabooga in #5522
• Update peft requirement from ==0.8.* to ==0.9.* by @dependabot in #5626
• Save the extensions after Gradio 4 by @oobabooga in #5632
• Revert gradio to 3.50.2 by @oobabooga in #5640
• Merge dev branch by @oobabooga in #5641
• Add cache_4bit option for ExLlamaV2 by @oobabooga in #5645
• Change cache_4bit to cache_q4, improve descriptions by @bartowski1182 in #5649
• Merge dev branch by @oobabooga in #5655

Full Changelog: snapshot-2024-03-03...snapshot-2024-03-10

snapshot-2024-03-03

What's Changed

• Bump transformers to 4.38.1 for gemma compatibility by @bartowski1182 in #5575
• Bump hqq from 0.1.3 to 0.1.3.post1 by @dependabot in #5582
• Update llama2-chat-format.json by @jeffbiocode in #5593
• Cubic sampling w/ curve param by @kalomaze in #5551
• Merge dev branch by @oobabooga in #5617

Full Changelog: snapshot-2024-02-25...snapshot-2024-03-03

snapshot-2024-02-25

What's Changed

• Move chat UI elements to the right on desktop by @oobabooga in #5538
• Remove message.content from openai streaming API by @deoxykev in #5503
• Merge dev branch by @oobabooga in #5549
• Update accelerate requirement from ==0.25.* to ==0.27.* by @dependabot in #5546
• Bump autoawq from 0.1.8 to 0.2.2 by @dependabot in #5547
• Update optimum requirement from ==1.16.* to ==1.17.* by @dependabot in #5548
• Remove -k from curl command to download miniconda by @oobabooga in #5535
• ngrok logging does not use the shared logger module by @dsroark in #5570
• Llama2chatformat by @jeffbiocode in #5553
• Big picture fixes by @TheLounger in #5565
• Merge dev branch by @oobabooga in #5574

New Contributors

• @deoxykev made their first contribution in #5503
• @dsroark made their first contribution in #5570
• @jeffbiocode made their first contribution in #5553

Full Changelog: snapshot-2024-02-18...snapshot-2024-02-25