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

• 050682ab40 use invalid_gate consistently [pr] (#13374) chenyuandGitHub 2025-11-19 22:15:12 -05:00
• 2c8ad1b419 _apply_movement_op cache cache_reshape geohot 2025-11-19 16:10:00 -08:00
• 821f3771df AxisType.PLACEHOLDER in reshape to do less graph_rewrite geohot 2025-11-19 16:04:23 -08:00
• cb5d827ed9 use buf_target in expand_index bt_ei geohot 2025-11-19 15:37:19 -08:00
• 0dc2ff431d fix: revive torch backend (#13280) 3 people 2025-11-20 00:26:50 +01:00
• 56b2540349 tk: keep extra tile data by replacing uop (#13370) wozeparrotandGitHub 2025-11-19 15:11:43 -08:00
• ab7df42c78 bring back fold_divmod_general with bugfix and test [pr] (#13369) George HotzandGitHub 2025-11-19 14:51:51 -08:00
• 986d113024 symbolic fuzz failure (#13367) George HotzandGitHub 2025-11-19 14:21:08 -08:00
• 05ccc69248 Revert "merge to fold_divmod_general [p] (#13359)" geohot 2025-11-19 14:18:09 -08:00
• 90e5752199 Revert "actually merge to fold_divmod_general [pr] (#13363)" geohot 2025-11-19 14:18:08 -08:00
• 8e17bd6791 Revert "add cache to fold_divmod_general (#13365)" geohot 2025-11-19 14:18:08 -08:00
• b5309a5043 add cache to fold_divmod_general (#13365) George HotzandGitHub 2025-11-19 13:49:18 -08:00
• 3d82b83cec actually merge to fold_divmod_general [pr] (#13363) George HotzandGitHub 2025-11-19 13:17:56 -08:00
• a91f00925b remove VECTORIZE and WMMA rules from sym [pr] (#13362) chenyuandGitHub 2025-11-19 14:51:21 -05:00
• 7711bbac7f merge to fold_divmod_general [p] (#13359) George HotzandGitHub 2025-11-19 11:37:45 -08:00
• 6fdbd03104 more divmod cleanup [p] (#13358) George HotzandGitHub 2025-11-19 10:35:15 -08:00
• bd88a72149 div and mod to its own file, try 2 [p] (#13357) George HotzandGitHub 2025-11-19 10:10:06 -08:00
• 957cf717e7 Python speed (#13355) George HotzandGitHub 2025-11-19 09:03:00 -08:00
• 82aa943cd4 fix that test python_speed geohot 2025-11-19 08:48:49 -08:00
• fc19ea76b5 clean up threefry rules (#13354) chenyuandGitHub 2025-11-19 11:48:07 -05:00
• e16782cf9e Merge branch 'master' into python_speed George HotzandGitHub 2025-11-19 08:41:40 -08:00
• 1c47ee729e fix names of rewrite rules geohot 2025-11-19 08:41:34 -08:00
• a8f9e69bd9 work on python speed geohot 2025-11-19 08:34:15 -08:00
• 385618d45b skip process replay by default (#13353) George HotzandGitHub 2025-11-19 08:25:34 -08:00
• ffff194e93 skip process replay by default geohot 2025-11-19 08:14:44 -08:00
• fba4535289 remove hacks for threefry long removal when padded [pr] (#13352) chenyuandGitHub 2025-11-19 11:11:39 -05:00
• 225eb1500f generic range changes that work for str + int (#13350) George HotzandGitHub 2025-11-19 08:07:49 -08:00
• 1a72ac16a6 move where same false branch rule to symbolic_simple [pr] (#13349) chenyuandGitHub 2025-11-19 10:15:38 -05:00
• 79055ddb8b clean propagate_invalid more [pr] (#13347) chenyuandGitHub 2025-11-19 09:47:50 -05:00
• 0c9fbf87e1 nvioctl: classes (#13346) nimlgenandGitHub 2025-11-19 16:14:15 +03:00
• f2221130bb viz: pick shape by event type (#13279) qazalandGitHub 2025-11-19 20:15:52 +08:00
• be72b78dcb tk: small fixes (#13345) wozeparrotandGitHub 2025-11-19 00:58:50 -08:00
• e4fbde5b3b fix: extra options need to go on second step too (#13344) wozeparrotandGitHub 2025-11-19 00:58:09 -08:00
• 1a332afa76 spec test on 3.14 (#12957) George HotzandGitHub 2025-11-19 00:43:04 -08:00
• 8ba57c3246 we name the warp warp now string_ranges geohot 2025-11-18 22:17:18 -08:00
• a438c277de autogen tests for 3.14 (#13343) sirhcmandGitHub 2025-11-18 22:16:59 -05:00
• 722e7a16ed remove rule in propagate_invalid [pr] (#13342) chenyuandGitHub 2025-11-18 21:38:33 -05:00
• a3490252e2 fix negative geohot 2025-11-18 17:28:42 -08:00
• db150af97e str in limit_bufs geohot 2025-11-18 17:19:39 -08:00
• e473daff5a str geohot 2025-11-18 17:15:52 -08:00
• 1852463f24 string_ranges geohot 2025-11-18 17:12:09 -08:00
• 1afa3c0877 vmap on full model (#13340) George HotzandGitHub 2025-11-18 16:06:06 -08:00
• 46cb65e692 delete rules from sym [pr] (#13339) chenyuandGitHub 2025-11-18 14:57:35 -05:00
• 278ca0388b scan with assign scan_assign geohot 2025-11-18 11:02:22 -08:00
• 9c59b3d19e vmap grad needs reduce_backward (#13336) George HotzandGitHub 2025-11-18 10:08:30 -08:00
• a647c9eca6 sqtt ui minor fixes (#13335) qazalandGitHub 2025-11-19 01:27:56 +08:00
• 06e39a88a9 outer vmap works (#13334) George HotzandGitHub 2025-11-18 09:27:48 -08:00
• 805de27e07 no load substitute in uop_given_valid [pr] (#13333) chenyuandGitHub 2025-11-18 11:47:58 -05:00
• 05294bc648 fix some mypy cast [pr] (#13331) chenyuandGitHub 2025-11-18 09:23:42 -05:00
• 5623e765c8 VIZ=2 enables SQTT (#13330) qazalandGitHub 2025-11-18 22:20:31 +08:00
• 331f70aa75 roc: ctrlc (#13255) nimlgenandGitHub 2025-11-18 14:29:28 +03:00
• 583560ab72 this is the right way to write vmap (#13328) George HotzandGitHub 2025-11-17 20:20:52 -08:00
• 50fd47d239 never mind, i don't like this more_vmap geohot 2025-11-17 19:47:08 -08:00
• a6e976b2d8 works geohot 2025-11-17 19:22:26 -08:00
• e279c80631 outer vmap geohot 2025-11-17 19:01:14 -08:00
• 8e8e53c886 int8_t is c_byte (#13326) sirhcmandGitHub 2025-11-17 21:25:40 -05:00
• efc7d5f1b6 scan op work scan_op_8 geohot 2025-11-17 18:09:17 -08:00
• e4fead8a86 write scan in uops (#13321) George HotzandGitHub 2025-11-17 16:58:08 -08:00
• 8894a5409d feat: hipcc compiler (#13319) wozeparrotandGitHub 2025-11-17 15:13:32 -08:00
• 6d3385c284 print special ops in postrange (#13318) George HotzandGitHub 2025-11-17 14:43:23 -08:00
• 28c2776999 fix on OSX print_special_ops geohot 2025-11-17 14:19:39 -08:00
• b637093be9 remove a few rules in pm_lower_index_dtype [pr] (#13317) chenyuandGitHub 2025-11-17 14:04:56 -08:00
• e13580a1d7 print special ops in postrange geohot 2025-11-17 13:35:29 -08:00
• 98e9e73286 hotfix: amd_uop_matmul getenvs geohot 2025-11-17 13:25:51 -08:00
• e7e1935225 cleanup sqtt/test_timing (#13315) qazalandGitHub 2025-11-18 04:28:05 +08:00
• 33773fda87 tk initial mi350 (#13289) wozeparrotandGitHub 2025-11-17 11:46:32 -08:00
• e2cee64050 Revert "hcq: add tag to exec events (#13311)" (#13314) nimlgenandGitHub 2025-11-17 22:15:31 +03:00
• 646372490c move tiktoken import in llama3 (#13316) chenyuandGitHub 2025-11-17 11:09:37 -08:00
• df2f3457e4 Revert "hcq: add tag to exec events (#13311)" revert-13311-prof_link_sqtt nimlgenandGitHub 2025-11-17 21:08:17 +03:00
• a37f221e44 viz: visualize waves in the timeline (#13292) qazalandGitHub 2025-11-17 22:04:21 +08:00
• f63ded5817 hcq: add tag to exec events (#13311) nimlgenandGitHub 2025-11-17 16:59:30 +03:00
• 50a443f558 viz: add shader engine to wave exec payload (#13310) qazalandGitHub 2025-11-17 19:11:34 +08:00
• 9bb17c53ea amd: timer fix (#13267) nimlgenandGitHub 2025-11-17 13:59:03 +03:00
• 55be95da15 cleanup sqtt raw parser (#13309) George HotzandGitHub 2025-11-16 13:11:51 -08:00
• cabd4add48 more work parsing SQTT, separate VIZ/PROFILE (#13308) George HotzandGitHub 2025-11-16 10:40:39 -08:00
• f8ff531b68 AQL in mmapeak parse_sqtt_more geohot 2025-11-16 10:15:45 -08:00
• c9254c32df skip flaky test geohot 2025-11-16 09:58:52 -08:00
• ddaaeb16de lil cleanup geohot 2025-11-16 09:48:19 -08:00
• 5fba9ccb85 split them geohot 2025-11-16 09:35:40 -08:00
• 2136c76fa8 that geohot 2025-11-16 09:31:16 -08:00
• f9f5fd2b41 more filter geohot 2025-11-16 09:20:20 -08:00
• dac087f2b7 improve parser geohot 2025-11-16 09:08:42 -08:00
• 1129e4c5d5 parse print new geohot 2025-11-16 09:04:41 -08:00
• aaec1130a3 sep VIZ/PROFILE geohot 2025-11-16 08:59:50 -08:00
• 13efdf8c31 test s_nop stall (#13307) qazalandGitHub 2025-11-17 00:59:39 +08:00
• 24c7f38105 more minimal runner geohot 2025-11-16 08:48:13 -08:00
• 22432917d3 more work parsing SQTT geohot 2025-11-16 08:28:38 -08:00
• 295600dc5a saturday coffee shop work parsing the att format (#13295) George HotzandGitHub 2025-11-16 08:25:51 -08:00
• a9ed241172 properly suppress NIRRenderer.__del__ error (#13299) sirhcmandGitHub 2025-11-16 10:58:04 -05:00
• c70b06ec19 sqtt test_timing work (#13304) qazalandGitHub 2025-11-16 23:49:24 +08:00
• a0c8d04feb grad outerworld test grad_outerworld geohot 2025-11-16 07:43:51 -08:00
• 8f0e747b3a Tensor._tri with arange (#13297) chenyuandGitHub 2025-11-16 07:21:16 -08:00
• 6372c95094 disable benchmark MobileNetV2 on DSP (#13305) chenyuandGitHub 2025-11-16 06:42:52 -08:00
• 61625a3898 fix objc finalizing bug (#13296) sirhcmandGitHub 2025-11-16 04:43:04 -05:00
• acbe6361ab qcom: suppress_finalizing to free (#13294) nimlgenandGitHub 2025-11-16 11:49:23 +03:00
• ef42334239 tk: load store cleanup (#13290) wozeparrotandGitHub 2025-11-15 17:08:23 -08:00
• e8844853ed Tensor.eye with arange (#13287) chenyuandGitHub 2025-11-15 09:32:27 -08:00
• 5b823af696 Remove (pypi) clang dep for autogen (#13284) 3 people 2025-11-15 12:05:11 -05:00
• df53c62a9f bump line count geohot 2025-11-15 08:16:20 -08:00
• d37e1fe065 nv: wait for wpr to reset (#13282) nimlgenandGitHub 2025-11-15 20:00:49 +08:00