oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-12-06 07:12:10 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
5082 commits 6 branches 88 tags 66 MiB
Commit graph

197 commits

Author SHA1 Message Date
oobabooga 877cf44c08 llama.cpp: Add StreamingLLM (--streaming-llm) 2025-04-25 16:21:41 -07:00
oobabooga 98f4c694b9 llama.cpp: Add --extra-flags parameter for passing additional flags to llama-server 2025-04-25 07:32:51 -07:00
oobabooga 93fd4ad25d llama.cpp: Document the --device-draft syntax 2025-04-24 09:20:11 -07:00
oobabooga e99c20bcb0
llama.cpp: Add speculative decoding (#6891) 2025-04-23 20:10:16 -03:00
oobabooga ae02ffc605
Refactor the transformers loader (#6859) 2025-04-20 13:33:47 -03:00
oobabooga d68f0fbdf7 Remove obsolete references to llamacpp_HF 2025-04-18 07:46:04 -07:00
oobabooga 8144e1031e Remove deprecated command-line flags 2025-04-18 06:02:28 -07:00
oobabooga ae54d8faaa
New llama.cpp loader (#6846) 2025-04-18 09:59:37 -03:00
oobabooga 2c2d453c8c Revert "Use ExLlamaV2 (instead of the HF one) for EXL2 models for now" 
This reverts commit 0ef1b8f8b4.
 2025-04-17 21:31:32 -07:00
oobabooga 0ef1b8f8b4 Use ExLlamaV2 (instead of the HF one) for EXL2 models for now 
It doesn't seem to have the "OverflowError" bug
 2025-04-17 05:47:40 -07:00
oobabooga bf48ec8c44 Remove an unnecessary UI message 2025-04-07 17:43:41 -07:00
oobabooga a5855c345c
Set context lengths to at most 8192 by default (to prevent out of memory errors) (#6835) 2025-04-07 21:42:33 -03:00
oobabooga 75ff3f3815 UI: Mention common context length values 2025-01-25 08:22:23 -08:00
oobabooga 3020f2e5ec UI: improve the info message about --tensorcores 2025-01-09 12:44:03 -08:00
oobabooga 7157257c3f
Remove the AutoGPTQ loader (#6641) 2025-01-08 19:28:56 -03:00
oobabooga c0f600c887 Add a --torch-compile flag for transformers 2025-01-05 05:47:00 -08:00
oobabooga 39a5c9a49c
UI organization (#6618) 2024-12-29 11:16:17 -03:00
oobabooga ddccc0d657 UI: minor change to log messages 2024-12-17 19:39:00 -08:00
oobabooga 3030c79e8c UI: show progress while loading a model 2024-12-17 19:37:43 -08:00
Diner Burger addad3c63e
Allow more granular KV cache settings (#6561) 2024-12-17 17:43:48 -03:00
mefich 1c937dad72
Filter whitespaces in downloader fields in model tab (#6518) 2024-11-18 12:01:40 -03:00
oobabooga 93c250b9b6 Add a UI element for enable_tp 2024-10-01 11:16:15 -07:00
oobabooga 7050bb880e UI: make n_ctx/max_seq_len/truncation_length numbers rather than sliders 2024-07-27 23:11:53 -07:00
Harry 078e8c8969
Make compress_pos_emb float (#6276) 2024-07-28 03:03:19 -03:00
oobabooga e6181e834a Remove AutoAWQ as a standalone loader 
(it works better through transformers)
 2024-07-23 15:31:17 -07:00
oobabooga f18c947a86 Update the tensorcores description 2024-07-22 18:06:41 -07:00
oobabooga aa809e420e Bump llama-cpp-python to 0.2.83, add back tensorcore wheels 
Also add back the progress bar patch
 2024-07-22 18:05:11 -07:00
oobabooga 11bbf71aa5
Bump back llama-cpp-python (#6257) 2024-07-22 16:19:41 -03:00
oobabooga 0f53a736c1 Revert the llama-cpp-python update 2024-07-22 12:02:25 -07:00
oobabooga a687f950ba Remove the tensorcores llama.cpp wheels 
They are not faster than the default wheels anymore and they use a lot of space.
 2024-07-22 11:54:35 -07:00
oobabooga e9d4bff7d0 Update the --tensor_split description 2024-07-20 22:04:48 -07:00
oobabooga 564d8c8c0d Make alpha_value a float number 2024-07-20 20:02:54 -07:00
oobabooga 79c4d3da3d
Optimize the UI (#6251) 2024-07-21 00:01:42 -03:00
Vhallo a9a6d72d8c
Use gr.Number for RoPE scaling parameters (#6233) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2024-07-20 18:57:09 -03:00
oobabooga e436d69e2b Add --no_xformers and --no_sdpa flags for ExllamaV2 2024-07-11 15:47:37 -07:00
oobabooga c176244327 UI: Move cache_8bit/cache_4bit further up 2024-07-05 12:16:21 -07:00
oobabooga e79e7b90dc UI: Move the cache_8bit and cache_4bit elements up 2024-07-04 20:21:28 -07:00
oobabooga 8b44d7b12a Lint 2024-07-04 20:16:44 -07:00
GralchemOz 8a39f579d8
transformers: Add eager attention option to make Gemma-2 work properly (#6188) 2024-07-01 12:08:08 -03:00
oobabooga 577a8cd3ee
Add TensorRT-LLM support (#5715) 2024-06-24 02:30:03 -03:00
oobabooga b48ab482f8 Remove obsolete "gptq_for_llama_info" message 2024-06-23 22:05:19 -07:00
GodEmperor785 2c5a9eb597
Change limits of RoPE scaling sliders in UI (#6142) 2024-06-19 21:42:17 -03:00
Forkoz 1d79aa67cf
Fix flash-attn UI parameter to actually store true. (#6076) 2024-06-13 00:34:54 -03:00
oobabooga 2d196ed2fe Remove obsolete pre_layer parameter 2024-06-12 18:56:44 -07:00
oobabooga 4f1e96b9e3 Downloader: Add --model-dir argument, respect --model-dir in the UI 2024-05-23 20:42:46 -07:00
oobabooga 9e189947d1 Minor fix after bd7cc4234d (thanks @belladoreai) 2024-05-21 10:37:30 -07:00
oobabooga bd7cc4234d
Backend cleanup (#6025) 2024-05-21 13:32:02 -03:00
Samuel Wein b63dc4e325
UI: Warn user if they are trying to load a model from no path (#6006) 2024-05-19 20:05:17 -03:00
chr 6b546a2c8b
llama.cpp: increase the max threads from 32 to 256 (#5889) 2024-05-19 20:02:19 -03:00
oobabooga e61055253c Bump llama-cpp-python to 0.2.69, add --flash-attn option 2024-05-03 04:31:22 -07:00
oobabooga 51fb766bea
Add back my llama-cpp-python wheels, bump to 0.2.65 (#5964) 2024-04-30 09:11:31 -03:00
oobabooga f0538efb99 Remove obsolete --tensorcores references 2024-04-24 00:31:28 -07:00
wangshuai09 fd4e46bce2
Add Ascend NPU support (basic) (#5541) 2024-04-11 18:42:20 -03:00
Alex O'Connell b94cd6754e
UI: Respect model and lora directory settings when downloading files (#5842) 2024-04-11 01:55:02 -03:00
oobabooga d423021a48
Remove CTransformers support (#5807) 2024-04-04 20:23:58 -03:00
oobabooga 2a92a842ce
Bump gradio to 4.23 (#5758) 2024-03-26 16:32:20 -03:00
oobabooga 49b111e2dd Lint 2024-03-17 08:33:23 -07:00
oobabooga 40a60e0297 Convert attention_sink_size to int (closes #5696) 2024-03-13 08:15:49 -07:00
oobabooga 63701f59cf UI: mention that n_gpu_layers > 0 is necessary for the GPU to be used 2024-03-11 18:54:15 -07:00
oobabooga 056717923f Document StreamingLLM 2024-03-10 19:15:23 -07:00
oobabooga 15d90d9bd5 Minor logging change 2024-03-10 18:20:50 -07:00
oobabooga afb51bd5d6
Add StreamingLLM for llamacpp & llamacpp_HF (2nd attempt) (#5669) 2024-03-09 00:25:33 -03:00
Bartowski 104573f7d4
Update cache_4bit documentation (#5649) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2024-03-07 13:08:21 -03:00
oobabooga 2ec1d96c91
Add cache_4bit option for ExLlamaV2 (#5645) 2024-03-06 23:02:25 -03:00
oobabooga 2174958362
Revert gradio to 3.50.2 (#5640) 2024-03-06 11:52:46 -03:00
oobabooga 63a1d4afc8
Bump gradio to 4.19 (#5522) 2024-03-05 07:32:28 -03:00
oobabooga af0bbf5b13 Lint 2024-02-17 09:01:04 -08:00
oobabooga a6730f88f7
Add --autosplit flag for ExLlamaV2 (#5524) 2024-02-16 15:26:10 -03:00
oobabooga 76d28eaa9e
Add a menu for customizing the instruction template for the model (#5521) 2024-02-16 14:21:17 -03:00
oobabooga 44018c2f69
Add a "llamacpp_HF creator" menu (#5519) 2024-02-16 12:43:24 -03:00
oobabooga 080f7132c0
Revert gradio to 3.50.2 (#5513) 2024-02-15 20:40:23 -03:00
DominikKowalczyk 33c4ce0720
Bump gradio to 4.19 (#5419) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2024-02-14 23:28:26 -03:00
oobabooga b16958575f Minor bug fix 2024-02-13 19:48:32 -08:00
oobabooga d47182d9d1
llamacpp_HF: do not use oobabooga/llama-tokenizer (#5499) 2024-02-14 00:28:51 -03:00
oobabooga 2a1063eff5 Revert "Remove non-HF ExLlamaV2 loader (#5431)" 
This reverts commit cde000d478.
 2024-02-06 06:21:36 -08:00
oobabooga 7301c7618f Minor change to Models tab 2024-02-04 21:49:58 -08:00
oobabooga 9033fa5eee Organize the Model tab 2024-02-04 19:30:22 -08:00
Forkoz 2a45620c85
Split by rows instead of layers for llama.cpp multi-gpu (#5435) 2024-02-04 23:36:40 -03:00
Badis Ghoubali 3df7e151f7
fix the n_batch slider (#5436) 2024-02-04 18:15:30 -03:00
oobabooga cde000d478
Remove non-HF ExLlamaV2 loader (#5431) 2024-02-04 01:15:51 -03:00
Forkoz 5c5ef4cef7
UI: change n_gpu_layers maximum to 256 for larger models. (#5262) 2024-01-17 17:13:16 -03:00
oobabooga cbf6f9e695 Update some UI messages 2023-12-30 21:31:17 -08:00
oobabooga 0e54a09bcb
Remove exllamav1 loaders (#5128) 2023-12-31 01:57:06 -03:00
oobabooga e83e6cedbe Organize the model menu 2023-12-19 13:18:26 -08:00
oobabooga de138b8ba6
Add llama-cpp-python wheels with tensor cores support (#5003) 2023-12-19 17:30:53 -03:00
oobabooga 0a299d5959
Bump llama-cpp-python to 0.2.24 (#5001) 2023-12-19 15:22:21 -03:00
oobabooga f6d701624c UI: mention that QuIP# does not work on Windows 2023-12-18 18:05:02 -08:00
Water 674be9a09a
Add HQQ quant loader (#4888) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-12-18 21:23:16 -03:00
oobabooga f1f2c4c3f4
Add --num_experts_per_token parameter (ExLlamav2) (#4955) 2023-12-17 12:08:33 -03:00
oobabooga 3bbf6c601d AutoGPTQ: Add --disable_exllamav2 flag (Mixtral CPU offloading needs this) 2023-12-15 06:46:13 -08:00
oobabooga 7f1a6a70e3 Update the llamacpp_HF comment 2023-12-12 21:04:20 -08:00
Morgan Schweers 602b8c6210
Make new browser reloads recognize current model. (#4865) 2023-12-11 02:51:01 -03:00
oobabooga 2a335b8aa7 Cleanup: set shared.model_name only once 2023-12-08 06:35:23 -08:00
oobabooga 7fc9033b2e Recommend ExLlama_HF and ExLlamav2_HF 2023-12-04 15:28:46 -08:00
oobabooga e0ca49ed9c
Bump llama-cpp-python to 0.2.18 (2nd attempt) (#4637) 
* Update requirements*.txt

* Add back seed
 2023-11-18 00:31:27 -03:00
oobabooga 9d6f79db74 Revert "Bump llama-cpp-python to 0.2.18 (#4611)" 
This reverts commit 923c8e25fb.
 2023-11-17 05:14:25 -08:00
oobabooga 8b66d83aa9 Set use_fast=True by default, create --no_use_fast flag 
This increases tokens/second for HF loaders.
 2023-11-16 19:55:28 -08:00
oobabooga 923c8e25fb
Bump llama-cpp-python to 0.2.18 (#4611) 2023-11-16 22:55:14 -03:00
oobabooga cd41f8912b Warn users about n_ctx / max_seq_len 2023-11-15 18:56:42 -08:00
oobabooga af3d25a503 Disable logits_all in llamacpp_HF (makes processing 3x faster) 2023-11-07 14:35:48 -08:00