github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-22 21:38:10 -05:00
Code Issues Packages Projects Releases Wiki Activity
10,490 Commits 204 Branches 14 Tags
remove_on_stack
Commit Graph

1248 Commits

Author SHA1 Message Date
wozeparrot
d269bc95fa faster tinychat (#5993) 2024-08-08 19:16:26 -07:00
George Hotz
bc55c8a30e pmatmul example + GB/s bugfix [run_process_replay] (#5974) 
* pmatmul example + bugfix

* improve pmatmul

* Update real_pmatmul.py
 2024-08-07 22:32:11 -07:00
George Hotz
bf8ec23b00 hotfix: contiguous on precompute_freqs_cis 2024-08-07 14:40:56 -07:00
wozeparrot
5808e8a30f mockgpu remu changes (#5925) 2024-08-05 19:26:58 -07:00
wozeparrot
6740a0a6a0 hip_ioctl changes (#5917) 2024-08-05 11:58:38 -07:00
chenyu
996ff0c135 pow(2) -> square in RMSNorm [run_process_replay] (#5901) 
reads nicer in metadata
 2024-08-04 14:21:31 -04:00
Elias Wahl
4a114756f6 New BERT dataloader (#5881) 
* One file == One topic

* update test

* new dataloader

* update train script

* get index is faster
 2024-08-02 15:12:23 -04:00
nimlgen
34168a64e3 optimize nv profiler (#5856) 
* nv profiler fix

* cleanup hcq a bit

* fixes

* fix

* typo

* all signals put timestamp

* a bit cleaner

* merge fields

* type

* import

* tiny fix
 2024-08-01 23:57:45 +03:00
Vyacheslav Pachkov
610e454132 fix opencl_ioctl on comma (#5814) 
- remove unused code
- add CP_REG_TO_MEM opcode
- fixed parse_cmd_buf for more than 1 command object by correcting
an offset
- fixed memory mappings for cases when memory was allocated with
KGSL_MEMFLAGS_USE_CPU_MAP.
KGSL_MEMFLAGS_USE_CPU_MAP: If set on call and return, the returned GPU
address will be 0. Calling mmap() will set the GPU address.
So there are no IOCTL_KGSL_GPUOBJ_INFO ioctls for that type of memory
and it resulted to crash right after get_mem.
 2024-07-30 20:44:06 -07:00
David Hou
9a485f36e4 shard kvcache (#5830) 2024-07-30 20:29:54 -07:00
George Hotz
4e89d45513 hotfix: put contiguous back in llama 2024-07-30 18:43:48 -07:00
George Hotz
21c5e8e1b7 extreme llama speed, 57.34 tok/s (#5827) 
* extreme llama speed

* mergable
 2024-07-30 18:32:09 -07:00
George Hotz
e6879035a0 work to make GEMV fast (#5824) 
* work to make GEMV fast

* half8 cast

* align struct

* fix amd

* float8 is a later problem
 2024-07-30 17:41:40 -07:00
Francis Lata
ce61be16f1 clean up how preprocessed folder is defined (#5813) 2024-07-30 12:35:26 -04:00
chenyu
471b188d79 fix mypy errors in latest mypy (#5794) 
* fix mypy errors in latest mypy

mypy has stricter partial and api arg checks now

* PYTHONPATH="."
 2024-07-29 14:53:30 -04:00
nimlgen
ea27ec4cd0 nv switch classlist_v2 to classlist (#5763) 
* nv switch classlist_v2 to classlist

* support in mockgpu

* fix mockgpu
 2024-07-28 20:24:42 +03:00
chenyu
3686b6726a move GraphException to jit.py (#5744) 
same place where GraphRunner is defined
 2024-07-26 19:01:12 -04:00
George Hotz
489a5b99a5 hotfix: triton_nv_matmul touchups 2024-07-24 23:24:29 +00:00
George Hotz
bf24be4c8c triton gets 163 TFLOPS on 4090 2024-07-24 18:32:29 +00:00
George Hotz
4d47968580 fix acc folding for NV tensor cores (#5658) 
* fix acc folding for NV tensor cores

* fix correctness of reduce_before_expand
 2024-07-23 13:03:02 -07:00
nimlgen
08a9c0ae5e hcq cache invalidation for beam (#5630) 
* nv full cache invalidation

* the same command on amd

* linter

* fix amd

* nv no hardcoded consts

* beam default
 2024-07-22 18:13:17 +03:00
George Hotz
6c6d74d922 parallel mcts (#5626) 
* start work on parallel mcts

* compile was linearizing twice

* typing + more early stopping

* fix compiler error
 2024-07-21 14:53:23 -07:00
George Hotz
ef179087a4 mcts exit condition wasn't right, also use it with BEAM>=100 (#5619) 
* mcts exit condition wasn't right, also use it with BEAM>=100

* mcts touchups

* clean up sample
 2024-07-21 10:16:47 -07:00
George Hotz
0f67ef4674 mcts graph and dedup support (#5618) 
* mcts graph and dedup support

* usable graph

* mcts colors

* C=4 seems better

* C=3 even better

* sample_tree

* backprop is external function

* late expand to match algo
 2024-07-20 23:29:14 -07:00
chenyu
eddc5bcfd7 MCTS tweaks (#5616) 
MCTS 500 is competitive with BEAM=8 on resnet on M1 Max.
- increment trial times even with compiled error and runtime error.
- use best time of children as the node value.
 2024-07-20 19:45:59 -07:00
George Hotz
1113e47f96 print best in MCTS + light up the winner in hcopt 2024-07-20 09:39:36 -07:00
George Hotz
ac99ecd94e use statistics.median for timing (#5606) 2024-07-20 08:37:32 -07:00
George Hotz
06e336bccb mcts search (#5598) 
* mcts search

* mcts cleanups

* mcts cleanup

* random shuffle children order

* mcts in handcode_opt

* src and remove_node

* debug 3 to print ast

* print the type

* mcts in extra
 2024-07-19 21:38:39 -07:00
Tobias Fischer
72da3fe7e6 added clip vision model (#5595) 
Co-authored-by: chenyu <chenyu@fastmail.com>
 2024-07-19 18:35:51 -04:00
George Hotz
fa7e734b49 MetaOps.KERNEL (#5543) 2024-07-17 19:41:23 -07:00
Francis Lam
2d53abb04a test/external/fuzz_linearizer: fix for new AST changes (#5519) 
* test/external/fuzz_linearizer: fix for new AST changes

also add beautiful_mnist failures

* add CLANG and LLVM to test_failure_35 failed_platforms

* fix test_linearizer_failure names
 2024-07-17 00:08:07 -04:00
Tobias Fischer
85d4ca7caa FID Inception Model (#5516) 
* added model impl

* minor cleanups

* extracted weights loading into from_pretrained

* reorganized model for better weight loading

* removed lru cache for state dict loading
 2024-07-16 23:12:03 -04:00
chenyu
28972418c4 s/get_linearizer/get_kernel [run_process_replay] (#5467) 2024-07-13 20:32:22 -04:00
George Hotz
03c2dc8bd7 lowerer is kernel [run_process_replay] (#5437) 2024-07-12 18:50:55 -07:00
chenyu
00813a92a0 update Tensor.eye api to match torch (#5433) 
* update Tensor.eye api to match torch

input is n for nrows and optional m for ncols

* space

* fix onnx
 2024-07-12 20:25:12 -04:00
George Hotz
870dc8c350 s/Linearizer/Lowerer [run_process_replay] (#5428) 2024-07-12 15:54:07 -07:00
George Hotz
6707c778d0 scheduleitem is not Tuple [run_process_replay] (#5425) 
* scheduleitem is not Tuple [run_process_replay]

* fix tests

* fix op + fuzzers

* fix mop test
 2024-07-12 15:13:19 -07:00
George Hotz
94599c0637 fixup ast in kernel to be MetaOps.SINK [run_process_replay] (#5424) 
* fixup ast in kernel to be MetaOps.SINK [run_process_replay]

* fix tests

* fix more tests
 2024-07-12 14:01:03 -07:00
uuuvn
3cb94a0a15 Rename tinygrad/runtime/driver to support (#5413) 2024-07-12 11:06:42 -07:00
wozeparrot
a02b38c0ac download openimages by running it (#5396) 2024-07-11 16:06:13 -07:00
wozeparrot
fa873df9c1 bring tinychat more inline with tinyos' version (#5358) 2024-07-10 13:13:52 -07:00
George Hotz
c13da83f12 tests from lowerer branch (#5339) 
* tests from lowerer branch

* Update test_image_dtype.py

* Update test_image_dtype.py

* Update test_image_dtype.py
 2024-07-08 21:23:19 -07:00
nimlgen
51d6f372e4 nv get classes based on device (#5325) 
* nv get classes

* support in mockgpu

* choose sm based on gpu

* fix

* fix

* fix arch
 2024-07-08 18:25:05 +03:00
Tobias Fischer
0c3a35e5c2 Stable Diffusion v2 Inference (#5283) 
* model implementation

* clip fix, more qol options
 2024-07-03 22:47:10 -04:00
chenyu
b2c3a28a5e nn.RMSNorm (#5272) 
the norm itself has no significant value to add to Tensor method, but we would want Tensor.normalize
 2024-07-02 21:39:01 -04:00
Tobias Fischer
8c9c1cf62f Pulled CLIP and UNet into Seperate Files (#5253) 
* pulled clip and unet into seperate files

* reference cleanup, lru cache fix

* better pool indexing
 2024-07-01 22:33:01 -04:00
nimlgen
57e89645cd hcq spec test (#5226) 
* start hcq spec test

* more test

* fixes

* run on amd as well

* test amdgpu exec

* fix amd

* amd mockgpu support sdma timestamp
 2024-07-01 17:36:37 +03:00
George Hotz
14980f79dd hotfix: unbreak llama 2024-06-30 15:27:54 -07:00
George Hotz
3df47bc21e OpenELM + repeat_interleave (#5234) 
* start writing openelm

* progress...hit bug

* repeat_interleave support

* gqa

* add rotary embedding

* spp

* i think it runs correctly

* broken

* output is good now

* cleanups

* no io_uring on android
 2024-06-30 15:18:39 -07:00
nimlgen
dd7eef7d71 libc defs to autogen (#5217) 
* libc defs to autogen

* amd import libc

* linter

* better a bit

* remove comment, check this

* not hardcoded path
 2024-06-29 14:37:33 +03:00