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

• 36d679196c fix realize geohot 2025-10-01 14:29:00 +08:00
• 05e91a248d load alt value with cast (#12384) Sieds LyklesandGitHub 2025-10-01 07:14:26 +02:00
• 714500edfd viz: add font-weight to OffscreenCanvas config (#12390) qazalandGitHub 2025-10-01 08:08:47 +03:00
• a0fe1f68ec fix CL image thing geohot 2025-10-01 12:57:43 +08:00
• 57ad46c6e4 rangeify: increase atol for test_two_binops_no_rerun passing on real windows machine (#12389) b1tgandGitHub 2025-10-01 12:56:45 +08:00
• 6e8ab4c742 Merge branch 'master' into no_one_ranges George HotzandGitHub 2025-10-01 12:37:40 +08:00
• e02da8f5ac use op_in_parents (#12385) George HotzandGitHub 2025-10-01 12:37:29 +08:00
• 7d0c5a74e4 remove the ranges of 1 geohot 2025-10-01 12:36:02 +08:00
• 0662946fac atol in test_two_binops_no_rerun (#12387) chenyuandGitHub 2025-10-01 12:05:47 +08:00
• da52006bde rangeify: fix test_scatter_reduce (#12380) b1tgandGitHub 2025-10-01 11:26:36 +08:00
• bda35265b8 use op_in_parents geohot 2025-10-01 11:23:07 +08:00
• 1c1b4d14e9 minor cleaups in rangeify (#12382) George HotzandGitHub 2025-10-01 11:19:48 +08:00
• 4204edc60b feat: skip test_long (#12383) wozeparrotandGitHub 2025-09-30 20:07:39 -07:00
• 8def8145e4 ALLOWED_KERNEL_COUNT openpilot 0.9.4 with RANGEIFY (#12381) chenyuandGitHub 2025-10-01 10:58:59 +08:00
• 4c9a930de2 rangeify attn tests (#12377) George HotzandGitHub 2025-10-01 09:59:19 +08:00
• 26247573e1 rangeify multi tests on gpu (#12376) qazalandGitHub 2025-10-01 04:53:04 +03:00
• f2eb92948d rangeify: ban view pushing (#12371) qazalandGitHub 2025-10-01 04:37:52 +03:00
• a128fa0f8a removing double reshapes was wrong (#12375) George HotzandGitHub 2025-10-01 09:25:35 +08:00
• 969a1b35ca LR scheduler for Stable Diffusion mlperf training (#12201) hoovedandGitHub 2025-09-30 21:21:08 -04:00
• 9ef319f349 bad conv in rangeify (#12373) George HotzandGitHub 2025-10-01 08:56:22 +08:00
• 080b26e7d7 use suppress_finalizing to not mute all exceptions (#12372) nimlgenandGitHub 2025-09-30 21:24:31 +03:00
• 44558a37f7 fix some rangeify tests (#12370) George HotzandGitHub 2025-09-30 20:12:08 +08:00
• 2c397eb2a2 rangeify: buf limit (#12336) nimlgenandGitHub 2025-09-30 14:59:47 +03:00
• e7c7fdb47b now that needs rangeify 2 also fix_rangeify_tests geohot 2025-09-30 19:39:23 +08:00
• ed5592b858 Merge branch 'master' into fix_rangeify_tests George HotzandGitHub 2025-09-30 19:30:33 +08:00
• a83f219253 fix bad range merges (#12368) George HotzandGitHub 2025-09-30 19:30:21 +08:00
• 17a1777823 Merge branch 'master' into fix_rangeify_tests George HotzandGitHub 2025-09-30 19:29:50 +08:00
• 49dc879e8d fix some rangeify tests geohot 2025-09-30 19:23:42 +08:00
• a95159d579 remove TestShapeSpec, it relies on ShapeTracker [pr] (#12369) qazalandGitHub 2025-09-30 14:20:35 +03:00
• 7eee206177 fix uop gc geohot 2025-09-30 19:08:35 +08:00
• d8bb679a3a Merge branch 'master' into fix_rng_merge George HotzandGitHub 2025-09-30 18:59:08 +08:00
• c3f4ab1902 Merge branch 'master' into fix_range_merging_sd fix_range_merging_sd George HotzandGitHub 2025-09-30 18:50:13 +08:00
• c963e44ea0 that geohot 2025-09-30 18:50:04 +08:00
• 9cf5e66899 minimal rangeify stable diffusion fix (#12367) George HotzandGitHub 2025-09-30 18:48:35 +08:00
• b1f7ebd9f7 fix rng geohot 2025-09-30 18:36:27 +08:00
• b4a4817c9c fix rangeigy test_linalg (#12365) chenyuandGitHub 2025-09-30 18:28:35 +08:00
• de1d562b69 rangeify: update test_pickle asserts (#12366) qazalandGitHub 2025-09-30 13:27:41 +03:00
• dc11a23775 fix bad range merges geohot 2025-09-30 18:26:57 +08:00
• c9ef5d8fe5 rangeify: fix test_tensor_index_overflow (CPU_LLVM=1) (#12362) 3 people 2025-09-30 17:55:15 +08:00
• 036803f8e7 less topo geohot 2025-09-30 17:47:33 +08:00
• e8c595c29e remu: add new instructions introduced in RANGEIFY (#12363) qazalandGitHub 2025-09-30 12:36:29 +03:00
• e73f0bbf98 no repeating work with globals geohot 2025-09-30 17:35:25 +08:00
• 348188a0b5 ahh, that really fixes it geohot 2025-09-30 17:28:23 +08:00
• 8904b6b7d7 fix range merging for stable diffusion geohot 2025-09-30 17:05:32 +08:00
• 360980f1a3 work on rangeify cost function heuristics (#12360) George HotzandGitHub 2025-09-30 16:44:29 +08:00
• 9cd6e7c242 better cost function buf_heur geohot 2025-09-30 16:25:56 +08:00
• e090a2ad47 dedup geohot 2025-09-30 16:18:40 +08:00
• 109c63b904 update Tensor unit tests for RANGEIFY (#12359) qazalandGitHub 2025-09-30 11:17:21 +03:00
• b69b428e9f work on rangeify cost function heuristics geohot 2025-09-30 16:12:25 +08:00
• 7129419500 fix cifar training in RANGEIFY (#12355) George HotzandGitHub 2025-09-30 15:59:19 +08:00
• 4ff7f20b9d rangeify: fix kernelize (#12357) qazalandGitHub 2025-09-30 10:10:08 +03:00
• 86c5c969ea linalg cosmetic change (#12356) chenyuandGitHub 2025-09-30 15:00:59 +08:00
• 6a56d3c859 rangeify: only test correctness in multi (#12339) qazalandGitHub 2025-09-30 09:55:59 +03:00
• ab6b0d3a21 enable cleanup_dead_axes (#12351) George HotzandGitHub 2025-09-30 14:09:39 +08:00
• 2a7310ab59 rangeify: fix remaining multi correctness issue (#12354) qazalandGitHub 2025-09-30 08:08:27 +03:00
• 73b25bf47d z3 fix loaded mask (#12353) Sieds LyklesandGitHub 2025-09-30 06:55:50 +02:00
• 2a0caa09c2 push copy to disk (#12348) wozeparrotandGitHub 2025-09-29 21:55:05 -07:00
• 881709cd33 don't skip rangeify test_instancenorm_3d (#12350) chenyuandGitHub 2025-09-30 12:05:59 +08:00
• 39aae679e4 Support bfloat16 on NULL backend (#12340) hoovedandGitHub 2025-09-30 00:02:30 -04:00
• af935e7d32 Revert "reduce const folding (#12344)" (#12349) chenyuandGitHub 2025-09-30 11:45:30 +08:00
• f522e83a02 fix rangeify elu fusion for openpilot (#12341) George HotzandGitHub 2025-09-30 11:41:52 +08:00
• d95d018bb5 add name to multi rewrite [pr] (#12346) qazalandGitHub 2025-09-30 06:34:58 +03:00
• 05275c9ec3 rangeify: enable assign to mstack target (#12345) qazalandGitHub 2025-09-30 06:27:57 +03:00
• 8e508a9927 reduce const folding (#12344) chenyuandGitHub 2025-09-30 11:08:56 +08:00
• 3a480b858f use more getitem in gpt2 (#12343) chenyuandGitHub 2025-09-30 11:08:03 +08:00
• 32d69d07d7 rangeify: enable multitensor TestBatchNorm (#12342) qazalandGitHub 2025-09-30 06:05:00 +03:00
• d55d829635 Lower index dtype spec fix (#12337) Sieds LyklesandGitHub 2025-09-30 04:26:50 +02:00
• c38f6ce140 unified_rewrite: use deque and dont add nodes to the stack multiple times (#12320) 3 people 2025-09-30 04:02:28 +02:00
• c2689c505e Clip model updates for Stable Diffusion mlperf training (#12313) hoovedandGitHub 2025-09-29 21:50:14 -04:00
• cdfa0f29fd add rendering to index (#12338) George HotzandGitHub 2025-09-30 09:18:05 +08:00
• baf3b60cfb fix gpt2 on rangeify (#12335) George HotzandGitHub 2025-09-29 21:16:44 +10:00
• 9513f025c5 apply multi before rangeify (#12298) qazalandGitHub 2025-09-29 14:16:31 +03:00
• b899392f30 fix llm app with rangeify (#12334) George HotzandGitHub 2025-09-29 20:42:44 +10:00
• 7ae6898e31 better late bufferview (#12333) wozeparrotandGitHub 2025-09-29 03:08:34 -07:00
• 3291e00df7 fix efficientnet slowness on rangeify (#12332) George HotzandGitHub 2025-09-29 20:01:01 +10:00
• 9d2f2b8e34 skip test_mean_half_precision_overflow (#12331) chenyuandGitHub 2025-09-29 18:15:04 +09:00
• 9915bcf2b4 remove no-op contiguous from rand (#12329) qazalandGitHub 2025-09-29 11:53:16 +03:00
• 76c87d81b3 delete test_backward_sum_acc_dtype (#12330) chenyuandGitHub 2025-09-29 17:46:17 +09:00
• fd2e4f2353 failing rng test (#12328) George HotzandGitHub 2025-09-29 18:06:45 +10:00
• 29469577e8 tighten spec: fixup devectorizer types / rangeify (#12327) George HotzandGitHub 2025-09-29 17:41:11 +10:00
• a982480512 feat: late to_bufferview (#12271) wozeparrotandGitHub 2025-09-29 00:29:43 -07:00
• e01a3eb59a rangeify whitespace cleanups [pr] (#12326) qazalandGitHub 2025-09-29 10:04:51 +03:00
• cf925d1ac5 remove metadata for rangeify codegen (#12325) George HotzandGitHub 2025-09-29 16:29:28 +10:00
• b252f890da add support for SPEC=1 (#12322) George HotzandGitHub 2025-09-29 14:55:01 +10:00
• 292cb6ae26 viz: 404 if the requested rewrite doesn't exist (#12323) qazalandGitHub 2025-09-29 07:51:10 +03:00
• 250cb10e8f rangeify permuted assign (#12299) qazalandGitHub 2025-09-29 07:27:57 +03:00
• ed90de6583 Revert "Bufferize early, fix "children not making progress" on big graphs (#1…" (#12318) Sieds LyklesandGitHub 2025-09-28 19:10:21 +02:00
• 8b4a963789 Revert "Bufferize early, fix "children not making progress" on big graphs (#1…" revert-12308-bufferize_early Sieds LyklesandGitHub 2025-09-28 18:56:38 +02:00
• 29f0886395 skip test_softmax_fusion tests if RANGEIFY==1 (#12310) Sieds LyklesandGitHub 2025-09-27 05:57:40 +02:00
• b98f1881ef dsp opt test has different axis number on rangeify (#12309) Sieds LyklesandGitHub 2025-09-27 05:06:11 +02:00
• 6f1cf717de Bufferize early, fix "children not making progress" on big graphs (#12308) Sieds LyklesandGitHub 2025-09-27 04:17:15 +02:00
• 0104b16b9b rangeify: fix empty tags in reshapes (#12307) qazalandGitHub 2025-09-26 16:32:48 +03:00
• f5eb46a3d9 fix limit buf metal on non rangeify (#12303) nimlgenandGitHub 2025-09-26 11:06:28 +03:00
• 8b2e0930d7 rangeify: enable passing multi test (#12301) qazalandGitHub 2025-09-26 08:31:13 +03:00
• 74411984fc Rangeify IMAGE (#12304) Sieds LyklesandGitHub 2025-09-26 07:21:02 +02:00
• d2cd269e28 fix: try close mmap (#12306) wozeparrotandGitHub 2025-09-25 20:54:27 -07:00
• 17cec8d645 RANGEIFY winograd test (#12297) chenyuandGitHub 2025-09-24 23:42:32 -04:00
• 476a2a0a96 test_qcom: update (#12293) nimlgenandGitHub 2025-09-24 21:45:58 +03:00
• 38ecefaacb RANGEIFY=1 allreduce (#12260) qazalandGitHub 2025-09-24 18:13:08 +03:00
• 0e778296be rangeify: refactor const folding (#12291) qazalandGitHub 2025-09-24 17:58:39 +03:00