Commit Graph

Select branches

Hide Pull Requests

abstractions_4

add_local_buffer

after_qol

algebraic_upat

all_bv_no_idx

all_sink

amd_isel

amd_refac

amd_smu_reset_patch

amd_sqtt

amd_uop

amd_uop_cleanups

assign_copy

assign_try_3

autogen-comgr-2

before2

better_spec

better_syn

bitcast_spec

broadcast_shape_2

bt_ei

buf_heur

bump_nv_2404

cache_reshape

call_inline

call_is_kernels

callify

cast_vec_as_cast

cat_mop

changes_from_rangify

check_clsetarg

check_dims

ci-deps

cifar_30

cifar_30_clean

clean_load

clean_spec

clone_tg

codegen_try_2

contig_on_after

continue_mat

deepsek

default_late_allreduce

delete_kernel_py

delete_ones

delete_slow_rangeify

demote_op

disable_rules

dsp_search

dsp_search_merged

dtype_shape

earlier_gater

emu_cdna

emulate_ctx

end_all_ranges

endrange

er_prioity

execution_unit

explicit-dev

failing_assign

fancy_usb

fast_llm

fix_fa_fwd_clang_22

fix_fuse

fix_llvm_cast

fix_range_merging_sd

fix_rangeify_tests

fix_rc

fix_sched_copy

fix_slice_store

fix_src_spec

fixup_fix_kernel

full_spec

fun_w_egraphs

gate-on-load-store

gate_rewrite

gemma4_gpt

gen_pdf_fast

gh-pages

gitea-test-ci

gl_dims

gldims

glm_flash

grad_outerworld

grok_x86_novec

group_div_rules

heur_4096

heur_group

hk_gemm

http_threading

hwtest_fixes

id_store

if_range_cleanups

ignore_oob

image_idx_xy

image_in_mc

image_no_vec

image_refactors_stack

index_to_slice

invalid_try_3

jinja_template

kernel4

kernel_is_call

kernelless

kimi_slop

kitten_matmul

late_Locals

late_add_load

late_allreduce

late_codegen

late_decomp_is_late

late_lower_idx

late_view

late_weakint

lds_double_buffering

less_wmma_arg

lil_dg_change

lil_rangeify_td

llama_trainer

llm_262k_minimal

llm_flash_attn

llm_qwen

llm_serve_fixes

load_view_late

local_cache

locals_have_device

loop_end_op

loop_is_rng

lowerer_hacks

mac_pytest

manual_kernel_3

master

mega_lowerer

min_new_lin

min_outer_range

minor_views

mixins7

mlperf_training_v4.1

mlperf_training_v5.0

mlperf_training_v6.0

modern_scan

more_apps

more_early_comps

more_folding_rules

more_kernelcount

more_pcode

more_rangeify_pm_tests

more_ren_clean

more_uop_gc_test

more_uop_mm

more_vmap

move_devec

move_dtype_decomps

move_expander

move_gates_to_load_store

move_mop_cleanup

move_schedule

move_simp_views

moveleftright

mt_typing

multi_range

multioutput

new_ck

new_devec

new_invalid_and_image

new_linearizer

new_shape

new_test

no-chat-template

no_assign_2

no_buf_0

no_decimals

no_late_simplify_marg

no_merge_ends

no_merge_views

no_mstack_in_allreduce

no_one_ranges

no_sip_usbgpu

no_tsink_base

no_tuplize

no_user_ck_contig

no_vec_x86_4

noop_index

novecimg

num_batches_tracked_shape

olmo3_support

one_compiler

one_hcopt

only_assign_buffers

only_loop_backends

only_reg_emu

only_reg_emu2

onnx-cpu-count

outer_range

outerworld_work

pad_invalid

pad_invalid_work

pad_mixin

param_call_is_function

parse_sqtt_more

pci_iommu

port_nir

postrange_hcopts

precompile_backward

prefill_qwen_fast

print_special_ops

ps_clean

pyremu_try

python_prg

python_speed

q4k_support

qcom-openpilot-13ms

qcom_830

qcom_mmapeak

qcom_speed_codex

qol_string

qwen36_27b_amd_900

qwen36_27b_amd_minimal

qwen36_amd_bugfixes

r_cleanups

r_new_opt

ranged_call

rangeify_2

rangeify_const_folding

rdna3_vibes

rdna4_asm

rdna4_gemm

real_pyrender

recurse_sub

reg_coalese

relu_pattern

remove_assign

remove_cast_hack

remove_ck_contig

remove_define_var

remove_forced_re

remove_on_stack

remove_programspec

remove_pylint

remove_slow_tests

remove_vec_2

remove_vec_3

renderers_use_shapes_2

replace_if_with_range

reprocess_node_experiments

reshape_trait

resnet-ci

revert-11547-fix_mismatch_red

revert-11715-revert-11711-amd_llvm_tc_cast

revert-11809-no_ki_in_gpudims

revert-11811-better_div_nesting

revert-11876-memplan_vbig

revert-12104-simplify_valid_in_symbolic

revert-12308-bufferize_early

revert-12731-jitlink_init_check

revert-12813-after_cleanups

revert-13046-better_cleanup_arange_buffers

revert-13311-prof_link_sqtt

revert-13583-rocr_desc_2

revert-14734-tload

revert-17141-full_rewrite_to_sink

revert-17408-_broadcasted-weak

revert-9438-simple_matmul_np_rand

revert_wrong_ck_fix

rewrite_rangeify2

rtoposort

scan_assign

scan_op_8

sched_cache

sched_lin

sd_load_simple

self_type

set_testpath

shrink_in_render

simp_spec

simple_gidxs

simple_pool

simple_priority

simple_rangeify

simpler-sd-compile

simpler_end

simpler_fusion

simpler_image

simpler_postrange

simpler_reduce

slice_like_shrink

spec_3

spec_cleanup

spec_ren

speed_one_linear

split_buf_idx

split_decomp_pass

split_sub

stack_0

store_is_void

string_ranges

support_opts_in_contig

swizzle_in_kernel

sym_llm

sym_work

symbolic-chunk-split

szdiff_bot_test

tc_is_heur

tensor_graph_single_sink

test-lp

test_amd_crash

test_fa

test_from_postopt

test_hgemm

test_unit

tiny_scan

tmr

tool_call_support

topoprop

ttomsa-new_linearizer

tuplegtuple

two_stage_remove

typed_checks

typing_work

unused_permute_arg

uop_prg

upd_test4

update_benchmark

update_benchmark_search

update_mlperf

user_failure

vecless_x86_glm

verify_sink_dims_clean

view_after_const

view_in_codegen

viz_cbroadcast

warp_fun

wgpu-f16-packed

working_postopt

x86_moves

x86_numel

#1

#2

#3

#4

#5

v0.10.0

v0.10.1

v0.10.2

v0.10.3

v0.11.0

v0.12.0

v0.13.0

v0.4.0

v0.5.0

v0.6.0

v0.7.0

v0.8.0

v0.9.0

v0.9.1

v0.9.2

Mono Color

• 08ec4de6a3 beautiful mnist is close geohot 2025-08-15 18:31:14 -07:00
• 7dc708e735 ops fixed geohot 2025-08-15 18:05:54 -07:00
• 65cbf9d785 late children geohot 2025-08-15 17:51:58 -07:00
• b3f5852fae unbind_kernel geohot 2025-08-15 17:19:36 -07:00
• 780a49ebfb symbolic in schedule geohot 2025-08-15 16:43:13 -07:00
• d1d4bbe179 contigs only geohot 2025-08-15 16:18:28 -07:00
• 998775507d basic assign geohot 2025-08-15 16:10:32 -07:00
• 14e055a8b6 progress counter geohot 2025-08-15 15:52:26 -07:00
• 8418d06300 progress geohot 2025-08-15 15:46:32 -07:00
• 4a6c2e5d68 new endrange solution geohot 2025-08-15 15:44:31 -07:00
• 58c8991fa4 add Ops.REWRITE_ERROR (#11689) qazalandGitHub 2025-08-16 00:56:53 +03:00
• 801712880e Merge branch 'master' into lil_rangeify George HotzandGitHub 2025-08-15 14:56:14 -07:00
• 20f8fe4443 progress children geohot 2025-08-15 14:53:13 -07:00
• 6425ed93c8 more stuff passes geohot 2025-08-15 14:37:53 -07:00
• ec4fccb1da viz: pass through RewriteNotReady (#11690) qazalandGitHub 2025-08-16 00:33:59 +03:00
• e48c87ba71 fix test_log_softmax geohot 2025-08-15 14:13:47 -07:00
• e954decb44 viz: pass UOp.st errors (#11688) qazalandGitHub 2025-08-16 00:07:56 +03:00
• 717b0d107c stuff passes geohot 2025-08-15 12:37:19 -07:00
• 2b93b50710 fix rangeify tests geohot 2025-08-15 12:08:52 -07:00
• bf0c45fd16 system: resource_resize might be unavail (#11680) nimlgenandGitHub 2025-08-15 22:03:23 +03:00
• e4884845a3 flash attention is back geohot 2025-08-15 11:18:45 -07:00
• d040d55960 Merge branch 'master' into lil_rangeify George HotzandGitHub 2025-08-15 11:08:50 -07:00
• 4ab9fb2edd explicit fixed point rewrite (#11685) George HotzandGitHub 2025-08-15 11:08:41 -07:00
• 5d6963c968 RuntimeError for unsupported dtype in PYTHON (#11686) chenyuandGitHub 2025-08-15 10:59:27 -07:00
• c707e87da0 fix rangeify geohot 2025-08-15 10:19:50 -07:00
• b970cd6895 am: fix psp ring completion (#11679) nimlgenandGitHub 2025-08-15 20:15:49 +03:00
• 155e97045d ish geohot 2025-08-15 10:11:28 -07:00
• 05f04bbcc3 work geohot 2025-08-15 09:47:38 -07:00
• c8ba48b223 show rewrite errors in viz (#11684) qazalandGitHub 2025-08-15 19:09:47 +03:00
• 551b34bb0f bufferize, don't use contig tag geohot 2025-08-15 09:00:18 -07:00
• 0575c95389 bring that over geohot 2025-08-15 08:54:33 -07:00
• 18130dae2a ** rangeify, try 3 geohot 2025-08-15 08:46:41 -07:00
• 560984fd8d small changes from rangeify (#11682) George HotzandGitHub 2025-08-15 08:45:52 -07:00
• 5766865193 Merge branch 'master' into no_merge_views no_merge_views George HotzandGitHub 2025-08-15 08:20:46 -07:00
• addd19d5e1 cleanups geohot 2025-08-14 19:11:46 -07:00
• d0d39885c3 onnx in tinygrad (#11675) chenyuandGitHub 2025-08-14 16:57:21 -07:00
• 66b92ffc82 one at a time geohot 2025-08-14 16:43:15 -07:00
• 71260a5ea4 feat: only bench openpilot 0.9.9 models (#11664) wozeparrotandGitHub 2025-08-14 19:27:18 -04:00
• 4ddefbccb4 update setup packages (#11674) chenyuandGitHub 2025-08-14 16:24:57 -07:00
• 35116959ea test mnist passes geohot 2025-08-14 16:24:32 -07:00
• 48c4033ae1 fix pylint for onnx (#11673) chenyuandGitHub 2025-08-14 15:48:02 -07:00
• ffa08e9c94 rangeify works again geohot 2025-08-14 15:04:41 -07:00
• c735855dc0 test_plus works geohot 2025-08-14 13:54:13 -07:00
• a5d3b54f47 work geohot 2025-08-14 13:52:14 -07:00
• 6131c0aad3 work geohot 2025-08-14 13:17:49 -07:00
• e9d0027591 llama MP realize weight after shard (#11672) chenyuandGitHub 2025-08-14 13:17:46 -07:00
• 46caa43733 k splitting geohot 2025-08-14 11:21:56 -07:00
• 4176b24264 amd: support xcc in regs (#11670) nimlgenandGitHub 2025-08-14 21:20:11 +03:00
• f399d0d75d Render mod in terms of idiv (#11668) Sieds LyklesandGitHub 2025-08-14 19:59:39 +02:00
• d747eeed32 amd logs parser based on device (#11669) nimlgenandGitHub 2025-08-14 19:49:33 +03:00
• 1e904155e3 Add Onnx Huggingface to test/models/test_onnx.py (#11468) geohotstanandGitHub 2025-08-14 23:16:41 +08:00
• 4fd4e13fcf Merge branch 'master' into no_merge_views George HotzandGitHub 2025-08-14 08:07:52 -07:00
• ab4ccf56a7 no geohot 2025-08-14 08:07:06 -07:00
• 06beeb6e13 Nest div even if factor is negative (#11666) Sieds LyklesandGitHub 2025-08-14 13:58:59 +02:00
• 661e9a2d5d div_and_mod_folding refactor (#11585) Sieds LyklesandGitHub 2025-08-14 11:52:42 +02:00
• 332630ddb5 threefry one kernel geohot 2025-08-13 19:54:09 -07:00
• e5eae3f524 assign becomes store geohot 2025-08-13 19:11:59 -07:00
• cae3616a68 cleanups geohot 2025-08-13 19:02:53 -07:00
• 3aa80e7176 rangify bmnist geohot 2025-08-13 18:44:43 -07:00
• b1e2fb9afd rangeify in geohot 2025-08-13 18:28:19 -07:00
• 59bfab8a9b sym geohot 2025-08-13 17:49:54 -07:00
• b5d7d339f4 no range arg geohot 2025-08-13 17:43:17 -07:00
• 0fc43c2e54 fix test_const_tensor_index index (#11660) chenyuandGitHub 2025-08-13 16:50:16 -07:00
• b7c195bf7e Merge branch 'master' into no_merge_views George HotzandGitHub 2025-08-13 16:21:41 -07:00
• 4fe19eec72 Ops.TRUNC (#11659) chenyuandGitHub 2025-08-13 15:40:48 -07:00
• eb10a9c76a viz: always left align timeline values (#11658) qazalandGitHub 2025-08-13 23:55:28 +03:00
• 8592fba874 Merge branch 'master' into no_merge_views George HotzandGitHub 2025-08-13 12:46:52 -07:00
• 22bdf48cdd render ranges in viz, name gbufs with sizes. changes from rangeify (#11656) George HotzandGitHub 2025-08-13 12:46:16 -07:00
• 260da2017c fix unit test dtypes changes_from_rangify geohot 2025-08-13 12:15:12 -07:00
• 9b4da590bb remove need for cast_vec (#11653) George HotzandGitHub 2025-08-13 12:09:47 -07:00
• 65dcd6dd45 render ranges in viz, name gbufs with sizes. changes from rangeify geohot 2025-08-13 12:06:34 -07:00
• 10ffd7e17b simpler geohot 2025-08-13 11:42:42 -07:00
• e2873a3a41 [bounty] Muon optim (#11414) 3 people 2025-08-13 11:27:55 -07:00
• 94e6d84e32 rewrite Tensor.round to not use cast int (#11654) chenyuandGitHub 2025-08-13 10:51:08 -07:00
• 5489be812c random works geohot 2025-08-13 09:47:02 -07:00
• e3d8185ba4 ignore that geohot 2025-08-13 09:43:08 -07:00
• cbf85fbfd0 Merge branch 'master' into no_merge_views George HotzandGitHub 2025-08-13 09:40:44 -07:00
• d2521d828a transcendental+idiv+threefry are uop decompositions (#11636) George HotzandGitHub 2025-08-13 09:37:12 -07:00
• bd9c4ab2e1 fix that cast_vec_as_cast geohot 2025-08-13 09:32:50 -07:00
• 1b29ea3eaf cast vec is cast geohot 2025-08-13 09:28:33 -07:00
• cf7224ce3e fully lint onnx.py (#11647) geohotstanandGitHub 2025-08-13 23:22:06 +08:00
• 925555b62a Fix onnx Domain bug (#11650) geohotstanandGitHub 2025-08-13 23:20:50 +08:00
• 67df617fe1 add launch bounds to ptx (#11646) Sieds LyklesandGitHub 2025-08-13 13:05:39 +02:00
• 88f95e9f59 viz: minor fixups for firefox (#11645) qazalandGitHub 2025-08-13 17:59:28 +08:00
• 6f88eac0fc viz: refactor node and edge tagging (#11644) qazalandGitHub 2025-08-13 17:41:01 +08:00
• 8140bf9778 viz: create layout once (#11643) qazalandGitHub 2025-08-13 14:24:58 +08:00
• 3fb79bb43a minor onnx cleanups (#11642) chenyuandGitHub 2025-08-12 22:05:19 -07:00
• e9e5a08a04 simplify onnx cubic (#11641) chenyuandGitHub 2025-08-12 16:57:31 -07:00
• 18cdbec447 split decompositions pass (#11638) George HotzandGitHub 2025-08-12 12:56:05 -07:00
• 1e740b115f restore that split_decomp_pass geohot 2025-08-12 11:24:01 -07:00
• 2ef5255b09 pack load store early geohot 2025-08-12 11:00:14 -07:00
• d319a044a6 fix ptx geohot 2025-08-12 10:55:37 -07:00
• 27396b8eed split decompositions pass geohot 2025-08-12 10:42:20 -07:00
• 0d8a0d7a96 update test_multi_const_folding_tensor to include pow (#11635) chenyuandGitHub 2025-08-12 10:35:37 -07:00
• 4d6e407eb0 Extend fast_idiv to negative ints (#11632) Sieds LyklesandGitHub 2025-08-12 19:34:49 +02:00
• 17adbe86d8 hotfix: do not default to capturing args in track_rewrites (#11634) qazalandGitHub 2025-08-13 01:01:24 +08:00
• ad9dec25b3 combine onnx parser and onnx (#11485) 3 people 2025-08-13 00:56:39 +08:00
• 4c3982c44e Take sign out of mod (#11631) Sieds LyklesandGitHub 2025-08-12 18:44:36 +02:00
• e28605e324 rename profile point event fields [pr] (#11633) qazalandGitHub 2025-08-13 00:11:21 +08:00
• 8a7be0a747 metal: workaround for transfers sync issue (#11622) nimlgenandGitHub 2025-08-12 16:16:34 +03:00