forks/candle.git -

	Commit message (Expand)	Author	Age	Files	Lines
...
*	Move some safetensors bits in the candle-core crate.	laurent	2023-07-03	1	-31/+2
*	Add a flag for custom prompt.	laurent	2023-07-01	1	-2/+7
*	Early conversion for the llama weights.	laurent	2023-06-30	2	-45/+19
*	Add a const to easily tweak the dtype used for llama internal computations.	laurent	2023-06-30	1	-4/+8
*	Tweak the kv-cache flag.	laurent	2023-06-29	1	-4/+4
*	Add a flag.	laurent	2023-06-29	1	-6/+11
*	Enable the KV cache after fixing the caching length and the rope bits.	laurent	2023-06-29	1	-14/+21
*	Only narrow when needed + deactivate the kv cache.	laurent	2023-06-29	1	-2/+6
*	Add some KV cache to llama.	laurent	2023-06-29	1	-36/+72
*	Typo.	Nicolas Patry	2023-06-29	1	-1/+1
*	Putting back main.	Nicolas Patry	2023-06-29	1	-3/+2
*	Putting back seed.	Nicolas Patry	2023-06-29	1	-2/+6
*	Revert some changes.	Nicolas Patry	2023-06-29	1	-11/+6
*	Remove unwrap.	Nicolas Patry	2023-06-29	1	-132/+90
*	Moving llama to f16.	Nicolas Patry	2023-06-29	1	-78/+128
*	Add a seed parameter to llama.	laurent	2023-06-29	1	-13/+10
*	Simple example fix.	Ubuntu	2023-06-29	2	-48/+56
*	Merge pull request #19 from LaurentMazare/llama_safetensors	Nicolas Patry	2023-06-29	3	-97/+324
\|\
\| *	Final updates -> moving to deterministic for easier comparison.	Ubuntu	2023-06-28	2	-42/+120
\| *	Ok.	Ubuntu	2023-06-28	2	-58/+81
\| *	Tmp.	Ubuntu	2023-06-28	2	-82/+208
* \|	Simplify the pattern matching logic in the cuda backend.	laurent	2023-06-29	1	-0/+2
\|/
*	Add some helper functions.	laurent	2023-06-27	1	-6/+1
*	Cache the causal mask in llama.	laurent	2023-06-27	1	-17/+51
*	Refactor the hierarchy.	Nicolas Patry	2023-06-27	5	-0/+697