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

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

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

delta_attention

delta_attention_scan

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

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

gl_dims

gldims

glm_flash

grad_outerworld

grok_x86_novec

group_div_rules

hcq2_vram_copies

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_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

no_weakint_variable

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

outer_range

outerworld_work

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

qwen_mergable

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_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

vf_ish

view_after_const

view_in_codegen

viz_cbroadcast

warp_fun

wgpu-f16-packed

working_postopt

x86_moves

x86_numel

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

• 16f0edbe90 pass opts arg in get_program process replay [pr] (#11571) qazalandGitHub 2025-08-08 08:05:09 +08:00
• 960cc6533a pass through name function args in track_rewrites (#11572) qazalandGitHub 2025-08-08 07:28:52 +08:00
• efdf08f3e2 global rangeify geohot 2025-08-07 15:12:00 -07:00
• 9a2f55425b global rangeify geohot 2025-08-07 15:08:45 -07:00
• 1826004ef9 feat: add tinyos builder link (#11570) wozeparrotandGitHub 2025-08-07 17:42:18 -04:00
• 9ed409d0f8 Merge branch 'master' into no_merge_views George HotzandGitHub 2025-08-07 14:42:07 -07:00
• 82be8abfd2 move opt under codegen (#11569) George HotzandGitHub 2025-08-07 14:19:17 -07:00
• d3c8f09579 fix lil failure simpler_fusion geohot 2025-08-07 13:55:36 -07:00
• 702e38dc19 remove FUSE_ARANGE_UINT (#11567) chenyuandGitHub 2025-08-07 13:49:06 -07:00
• 3969d8574d Merge branch 'master' into simpler_fusion George HotzandGitHub 2025-08-07 13:46:42 -07:00
• 6ed2dfd187 delete the arange dim mismatch restriction (#11568) George HotzandGitHub 2025-08-07 13:46:17 -07:00
• 174747efb3 no copy geohot 2025-08-07 13:13:50 -07:00
• aaec715fa8 fuse_range + MSTACK fix geohot 2025-08-07 13:03:53 -07:00
• 7ae4335127 feat: generate blend index (#11566) wozeparrotandGitHub 2025-08-07 14:20:28 -04:00
• 594cbdc66f skip AM ResNet50 benchmark (#11565) chenyuandGitHub 2025-08-07 11:07:01 -07:00
• de7b4b10af Merge branch 'master' into simpler_fusion George HotzandGitHub 2025-08-07 10:46:54 -07:00
• aa1a6f2132 support threshold in Tensor.softplus (#11564) chenyuandGitHub 2025-08-07 10:43:18 -07:00
• 807392be8b Merge branch 'master' into simpler_fusion George HotzandGitHub 2025-08-07 10:41:11 -07:00
• 7ee3770961 FUSE_ARANGE=1 (#11427) 3 people 2025-08-07 10:32:34 -07:00
• 4dfcfb1ae5 Revert "Revert "viz: align-center checkbox (#11555)"" geohot 2025-08-07 08:15:57 -07:00
• 7e42427a7b Revert "Revert "viz: remove color for unbind step (#11554)"" geohot 2025-08-07 08:15:51 -07:00
• dc765fbeb7 Revert "viz: timeline perf (#11533)" geohot 2025-08-07 08:08:51 -07:00
• 5650c7b86c Revert "viz: remove color for unbind step (#11554)" geohot 2025-08-07 08:08:50 -07:00
• c52facfd29 Revert "viz: align-center checkbox (#11555)" geohot 2025-08-07 08:08:50 -07:00
• 974cfbe76d Revert "viz: add support for colored tooltip text (#11556)" geohot 2025-08-07 08:08:49 -07:00
• 3bf0db80ef Revert "viz: pick the largest rect for proxy fillColor (#11558)" geohot 2025-08-07 08:08:48 -07:00
• 27c3c67e7c Merge branch 'master' into simpler_fusion George HotzandGitHub 2025-08-07 07:59:07 -07:00
• 9764c6cdee fix mismatch reduce, try 2 (#11560) George HotzandGitHub 2025-08-07 07:57:58 -07:00
• 76079bc7f2 viz: pick the largest rect for proxy fillColor (#11558) qazalandGitHub 2025-08-07 21:40:17 +08:00
• 4f29a2c441 fix flaky test on macos (#11557) nimlgenandGitHub 2025-08-07 15:55:35 +03:00
• b3f7ea6f93 viz: add support for colored tooltip text (#11556) qazalandGitHub 2025-08-07 20:04:43 +08:00
• 91ec093464 viz: align-center checkbox (#11555) qazalandGitHub 2025-08-07 19:22:02 +08:00
• 1e205775bd viz: remove color for unbind step (#11554) qazalandGitHub 2025-08-07 19:16:21 +08:00
• 031f26632b viz: timeline perf (#11533) nimlgenandGitHub 2025-08-07 13:16:17 +03:00
• a1aa5670aa Revert "fix mismatch reduce (#11547)" (#11549) George HotzandGitHub 2025-08-06 22:43:15 -07:00
• 0dbaa6293c Merge branch 'master' into simpler_fusion George HotzandGitHub 2025-08-06 22:42:53 -07:00
• ede77facbb Revert "fix mismatch reduce (#11547)" revert-11547-fix_mismatch_red George HotzandGitHub 2025-08-06 22:42:34 -07:00
• 49d21a9055 fix mismatch reduce (#11547) George HotzandGitHub 2025-08-06 21:12:51 -07:00
• 625ecb9fec simpler fusion logic geohot 2025-08-06 17:53:28 -07:00
• b8791e962c don't merge views, mops in kernel geohot 2025-08-06 17:23:31 -07:00
• 21570545d3 move view pushing to codegen, try 2 (#11534) George HotzandGitHub 2025-08-06 15:58:38 -07:00
• 2d5bdc939d faster llama3 dataloader (#11540) wozeparrotandGitHub 2025-08-06 15:25:57 -07:00
• 80d9cced07 more test cleanups (#11544) George HotzandGitHub 2025-08-06 15:05:21 -07:00
• 6fd1332763 update some tests for less Kernel (#11543) George HotzandGitHub 2025-08-06 14:19:59 -07:00
• 09dc7af8e9 move bind to big graph (#11539) George HotzandGitHub 2025-08-06 13:27:51 -07:00
• 2e59c5c3a1 move view after const view_after_const geohot 2025-08-06 11:20:23 -07:00
• 7c5e115747 test_mismatch_reduce (#11538) George HotzandGitHub 2025-08-06 10:02:14 -07:00
• e7cfac01f8 test_mismatch_reduce tmr geohot 2025-08-06 09:49:37 -07:00
• 4fe11725c6 pass through sink arg, update linearizer test (#11536) George HotzandGitHub 2025-08-06 09:48:48 -07:00
• bfebb5c37b do store in the replace_buffers (#11535) George HotzandGitHub 2025-08-06 08:42:45 -07:00
• 1163292759 move onnx_parser into onnx (#11530) geohotstanandGitHub 2025-08-06 22:46:27 +08:00
• 7b16fadd87 load view late + simpler rewrite (#11525) George HotzandGitHub 2025-08-06 06:55:11 -07:00
• 930d8dae0c hcq: lazy prof signal allocation (#11531) nimlgenandGitHub 2025-08-06 15:28:11 +03:00
• eafc7fda12 upd perfetto (#11528) nimlgenandGitHub 2025-08-06 14:00:34 +03:00
• 1afb290027 ci: fix runner in nv (#11527) nimlgenandGitHub 2025-08-06 10:38:04 +03:00
• 61dae0685c viz: show total mem in tooltip (#11526) qazalandGitHub 2025-08-06 11:51:26 +08:00
• 4689d29f49 rewrite name load_view_late geohot 2025-08-05 20:28:15 -07:00
• 07f45be2a7 simpler replace buffers geohot 2025-08-05 20:14:07 -07:00
• 064c8e1b8b add the load view later geohot 2025-08-05 20:09:09 -07:00
• cf66df0ea6 put load early to make pointers match (#11524) George HotzandGitHub 2025-08-05 20:04:32 -07:00
• 92175626e3 prereqs: move views to codegen (#11522) George HotzandGitHub 2025-08-05 19:27:58 -07:00
• c9225d22ce only disable flaky test_jit_multidev_xfer (#11523) chenyuandGitHub 2025-08-05 19:17:25 -07:00
• 27b7680e03 prereqs: move views to codegen minor_views geohot 2025-08-05 18:49:17 -07:00
• 5fcdd2a480 fix st_vars view_in_codegen geohot 2025-08-05 18:47:01 -07:00
• 00d33d706e move views to codegen geohot 2025-08-05 18:44:26 -07:00
• f58fd3143d cleanup fix_kernel (#11520) George HotzandGitHub 2025-08-05 18:38:43 -07:00
• 29262a7543 fine for ptx fixup_fix_kernel geohot 2025-08-05 18:26:06 -07:00
• dcc6ddf0eb that hack broke things geohot 2025-08-05 18:24:58 -07:00
• d1d935242b Revert "fix tests" geohot 2025-08-05 18:06:27 -07:00
• 6b330f302d remote metal was flaky geohot 2025-08-05 17:50:14 -07:00
• a27019383d fix tests geohot 2025-08-05 17:45:35 -07:00
• 8b285e193a move those to fix_kernel_ops geohot 2025-08-05 17:07:12 -07:00
• f0c9b11b9e early meta ops geohot 2025-08-05 17:00:49 -07:00
• 1902a85ac1 early load buffer geohot 2025-08-05 16:56:10 -07:00
• b2fc111e3f cleanup fix_kernel geohot 2025-08-05 16:46:13 -07:00
• b2017dec02 move that swizzle_in_kernel geohot 2025-08-05 16:23:33 -07:00
• 35530b40fb Merge branch 'master' into swizzle_in_kernel George HotzandGitHub 2025-08-05 15:59:06 -07:00
• 067daee5be pin torch to 2.7.1 (#11519) George HotzandGitHub 2025-08-05 15:58:57 -07:00
• 259f207af6 Merge branch 'master' into swizzle_in_kernel George HotzandGitHub 2025-08-05 15:53:07 -07:00
• b39f43c46a optimize in rewrite, try 2 (#11518) George HotzandGitHub 2025-08-05 15:52:53 -07:00
• 07b0df0d86 hotfix: test tensor dims start at 1 geohot 2025-08-05 15:40:24 -07:00
• 4dabdf7c6d Revert "optimize in rewrite (#11516)" (#11517) George HotzandGitHub 2025-08-05 15:39:07 -07:00
• c632329943 Merge branch 'master' into swizzle_in_kernel George HotzandGitHub 2025-08-05 15:34:21 -07:00
• 3b777a9e05 optimize in rewrite (#11516) George HotzandGitHub 2025-08-05 15:33:26 -07:00
• 9c5e2b0113 move to codegen geohot 2025-08-05 15:04:03 -07:00
• 8a6f0f49ef bugfixes geohot 2025-08-05 14:48:51 -07:00
• 2b90cdb5d6 fix variables geohot 2025-08-05 14:44:02 -07:00
• 23eca7fc54 move that geohot 2025-08-05 14:05:05 -07:00
• 3f71dd5fd0 cleanup after geohot 2025-08-05 13:59:23 -07:00
• 7116948f34 move swizzle to kernel geohot 2025-08-05 13:19:24 -07:00
• ec676eddfa nv: move base address higher (#11514) nimlgenandGitHub 2025-08-05 22:42:53 +03:00
• 7703f8b805 viz: skip flops info if estimates is symbolic (#11513) qazalandGitHub 2025-08-06 03:12:52 +08:00
• fec7fbb824 fixup realize late_view geohot 2025-08-05 11:59:53 -07:00
• 6e39f041b7 don't merge views until we are in kernel land geohot 2025-08-05 11:42:18 -07:00
• fc4e713d1c jit graph split tests (#11507) nimlgenandGitHub 2025-08-05 21:32:37 +03:00
• c57fde51f9 move swizzler to opt (#11509) George HotzandGitHub 2025-08-05 11:31:30 -07:00
• ace8e9a706 fix test_conv2d_winograd (#11511) chenyuandGitHub 2025-08-05 09:15:46 -07:00
• 223aaa0492 clean up more conv tests (#11510) chenyuandGitHub 2025-08-05 09:15:30 -07:00
• 76e62a1c23 extract conv layer test logic (#11488) Garret CastroandGitHub 2025-08-05 08:15:54 -07:00
• 8b8bd6c534 make einsum generate same kernels (#11508) 3 people 2025-08-05 23:12:52 +08:00