Commit Graph

12 Commits

Author SHA1 Message Date
chenyu e356807696
tinytqdm.set_description and tinytrange (#5101) 2024-06-22 14:45:06 -04:00
chenyu dccefab23f
remove mixtral weight to clang first (#3792)
seems fine without it now
2024-03-17 23:33:17 -04:00
George Hotz 3527c5a9d2
add Tensor.replace (#3738)
* add Tensor.replace

* fix dtypes in that test

* should be replace

* and mixtral
2024-03-14 13:34:14 -07:00
George Hotz 3415b0ee54 hotfix: mixtral copies norms together for 2% speed 2024-03-11 01:28:03 +00:00
chenyu bad6adaf8c
add mixtral and 6 gpus cifar to tinybox ci (#3676)
* add mixtral and 6 gpus cifar to tinybox ci

* print total ram used at the end of loading
2024-03-10 18:25:31 -04:00
chenyu c3c35f9142
flag to profile mixtral - 1.7 tok/s now (#3104) 2024-01-12 18:54:27 -05:00
George Hotz f432ec9c33
Bitcast hip fix + fix mixtral (#3022)
* fix bitcast in hip

* wrong dtype for precast, double COPY
2024-01-05 14:51:25 -08:00
chenyu f88506e630
move gpt2/llama sampling inside the model call (#3013)
* move gpt2/llama sampling inside the model call

* argmax uses one more kernel
2024-01-04 17:01:50 -05:00
Ivan Vnučec 8d206f6bfd
fix help message (#2705)
llama -> mixtral
2023-12-10 22:04:35 -08:00
George Hotz 59ab3675a3
faster mixtral + green for new kernels (#2701)
* green for new kernels

* track ram
2023-12-10 19:04:58 -08:00
George Hotz b01e3907a1 mixtral touch up: two lines 2023-12-10 17:21:49 -08:00
George Hotz b3982187d1
Mixtral Example (#2691)
* mixtral

* simpler

* global counters

* simpler

* weights arg
2023-12-10 17:18:31 -08:00