1644 commits

Author	SHA1	Message	Date
oobabooga	b28fa86db6	Default --gpu-layers to 256	2025-05-06 17:51:55 -07:00
Downtown-Case	5ef564a22e	Fix model config loading in shared.py for Python 3.13 (#6961)	2025-05-06 17:03:33 -03:00
oobabooga	c4f36db0d8	llama.cpp: remove tfs (it doesn't get used)	2025-05-06 08:41:13 -07:00
oobabooga	05115e42ee	Set top_n_sigma before temperature by default	2025-05-06 08:27:21 -07:00
oobabooga	1927afe894	Fix top_n_sigma not showing for llama.cpp	2025-05-06 08:18:49 -07:00
oobabooga	d1c0154d66	llama.cpp: Add top_n_sigma, fix typical_p in sampler priority	2025-05-06 06:38:39 -07:00
mamei16	8137eb8ef4	Dynamic Chat Message UI Update Speed (#6952)	2025-05-05 18:05:23 -03:00
oobabooga	475e012ee8	UI: Improve the light theme colors	2025-05-05 06:16:29 -07:00
oobabooga	b817bb33fd	Minor fix after df7bb0db1f	2025-05-05 05:00:20 -07:00
oobabooga	f3da45f65d	ExLlamaV3_HF: Change max_chunk_size to 256	2025-05-04 20:37:15 -07:00
oobabooga	df7bb0db1f	Rename --n-gpu-layers to --gpu-layers	2025-05-04 20:03:55 -07:00
oobabooga	d0211afb3c	Save the chat history right after sending a message	2025-05-04 18:52:01 -07:00
oobabooga	690d693913	UI: Add padding to only show the last message/reply after sending a message ... To avoid scrolling	2025-05-04 18:13:29 -07:00
oobabooga	7853fb1c8d	Optimize the Chat tab (#6948)	2025-05-04 18:58:37 -03:00
oobabooga	b7a5c7db8d	llama.cpp: Handle short arguments in --extra-flags	2025-05-04 07:14:42 -07:00
oobabooga	4c2e3b168b	llama.cpp: Add a retry mechanism when getting the logits (sometimes it fails)	2025-05-03 06:51:20 -07:00
oobabooga	ea60f14674	UI: Show the list of files if the user tries to download a GGUF repository	2025-05-03 06:06:50 -07:00
oobabooga	b71ef50e9d	UI: Add a min-height to prevent constant scrolling during chat streaming	2025-05-02 23:45:58 -07:00
oobabooga	d08acb4af9	UI: Rename enable_thinking -> Enable thinking	2025-05-02 20:50:52 -07:00
oobabooga	4cea720da8	UI: Remove the "Autoload the model" feature	2025-05-02 16:38:28 -07:00
oobabooga	905afced1c	Add a --portable flag to hide things in portable mode	2025-05-02 16:34:29 -07:00
oobabooga	3f26b0408b	Fix after 9e3867dc83	2025-05-02 16:17:22 -07:00
oobabooga	9e3867dc83	llama.cpp: Fix manual random seeds	2025-05-02 09:36:15 -07:00
oobabooga	b950a0c6db	Lint	2025-04-30 20:02:10 -07:00
oobabooga	307d13b540	UI: Minor label change	2025-04-30 18:58:14 -07:00
oobabooga	55283bb8f1	Fix CFG with ExLlamaV2_HF (closes #6937)	2025-04-30 18:43:45 -07:00
oobabooga	a6c3ec2299	llama.cpp: Explicitly send cache_prompt = True	2025-04-30 15:24:07 -07:00
oobabooga	195a45c6e1	UI: Make thinking blocks closed by default	2025-04-30 15:12:46 -07:00
oobabooga	cd5c32dc19	UI: Fix max_updates_second not working	2025-04-30 14:54:05 -07:00
oobabooga	b46ca01340	UI: Set max_updates_second to 12 by default ... When the tokens/second at at ~50 and the model is a thinking model, the markdown rendering for the streaming message becomes a CPU bottleneck.	2025-04-30 14:53:15 -07:00
oobabooga	771d3d8ed6	Fix getting the llama.cpp logprobs for Qwen3-30B-A3B	2025-04-30 06:48:32 -07:00
oobabooga	1dd4aedbe1	Fix the streaming_llm UI checkbox not being interactive	2025-04-29 05:28:46 -07:00
oobabooga	d10bded7f8	UI: Add an enable_thinking option to enable/disable Qwen3 thinking	2025-04-28 22:37:01 -07:00
oobabooga	1ee0acc852	llama.cpp: Make --verbose print the llama-server command	2025-04-28 15:56:25 -07:00
oobabooga	15a29e99f8	Lint	2025-04-27 21:41:34 -07:00
oobabooga	be13f5199b	UI: Add an info message about how to use Speculative Decoding	2025-04-27 21:40:38 -07:00
oobabooga	c6c2855c80	llama.cpp: Remove the timeout while loading models (closes #6907)	2025-04-27 21:22:21 -07:00
oobabooga	ee0592473c	Fix ExLlamaV3_HF leaking memory (attempt)	2025-04-27 21:04:02 -07:00
oobabooga	70952553c7	Lint	2025-04-26 19:29:08 -07:00
oobabooga	7b80acd524	Fix parsing --extra-flags	2025-04-26 18:40:03 -07:00
oobabooga	943451284f	Fix the Notebook tab not loading its default prompt	2025-04-26 18:25:06 -07:00
oobabooga	511eb6aa94	Fix saving settings to settings.yaml	2025-04-26 18:20:00 -07:00
oobabooga	8b83e6f843	Prevent Gradio from saying 'Thank you for being a Gradio user!'	2025-04-26 18:14:57 -07:00
oobabooga	4a32e1f80c	UI: show draft_max for ExLlamaV2	2025-04-26 18:01:44 -07:00
oobabooga	0fe3b033d0	Fix parsing of --n_ctx and --max_seq_len (2nd attempt)	2025-04-26 17:52:21 -07:00
oobabooga	c4afc0421d	Fix parsing of --n_ctx and --max_seq_len	2025-04-26 17:43:53 -07:00
oobabooga	234aba1c50	llama.cpp: Simplify the prompt processing progress indicator ... The progress bar was unreliable	2025-04-26 17:33:47 -07:00
oobabooga	4ff91b6588	Better default settings for Speculative Decoding	2025-04-26 17:24:40 -07:00
oobabooga	bc55feaf3e	Improve host header validation in local mode	2025-04-26 15:42:17 -07:00
oobabooga	3a207e7a57	Improve the --help formatting a bit	2025-04-26 07:31:04 -07:00