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

• 1c8cb0769a am: autogen asic_regs (#16004) sirhcmandGitHub 2026-05-04 19:52:07 -07:00
• 5d9431ecb9 fix ptx geohot 2026-05-04 19:44:01 -07:00
• 0f3b12fcd8 fixes geohot 2026-05-04 19:30:25 -07:00
• 60c8542320 work geohot 2026-05-04 19:21:22 -07:00
• 4ec5487ad8 fix renderers geohot 2026-05-04 19:04:49 -07:00
• 995a787d6c fix llvm crash geohot 2026-05-04 18:52:22 -07:00
• 1b17762030 fix python geohot 2026-05-04 18:44:53 -07:00
• c0f443cf47 Merge branch 'master' into move_gates_to_load_store George HotzandGitHub 2026-05-04 18:35:26 -07:00
• 26406bed83 amd uses .valid, not index src valid (#16042) George HotzandGitHub 2026-05-04 18:35:15 -07:00
• ff1258feef fix tests geohot 2026-05-04 17:33:01 -07:00
• 51b13466dd fix amd geohot 2026-05-04 17:23:43 -07:00
• 416878db9e i hate ai geohot 2026-05-04 17:14:53 -07:00
• e00b3b4065 fix geohot 2026-05-04 17:09:59 -07:00
• d810bd2b41 Merge branch 'master' into move_gates_to_load_store George HotzandGitHub 2026-05-04 17:05:21 -07:00
• 09ec34437d fix oob validation geohot 2026-05-04 16:55:32 -07:00
• a357a0449a Tensor.div cleanup (#16041) chenyuandGitHub 2026-05-04 19:27:36 -04:00
• 36383298be move gates to load/store geohot 2026-05-04 14:56:37 -07:00
• 8f397f5c7c move load gates geohot 2026-05-04 14:45:42 -07:00
• 5b4f62519d cache buffer_views as well (#16039) nimlgenandGitHub 2026-05-05 00:00:09 +03:00
• 8e99c4f097 fetch checks sha256 (#16037) sirhcmandGitHub 2026-05-04 13:08:38 -07:00
• 1884f67a39 simplify full_rewrite_to_sink spec (#16035) George HotzandGitHub 2026-05-04 11:44:13 -07:00
• a4fccd23b2 remove kwargs in UOp.vectorize [pr] (#16034) chenyuandGitHub 2026-05-04 12:46:38 -04:00
• b1d88ebf02 viz/cli: aggregate flops in -t (#16031) qazalandGitHub 2026-05-04 17:35:02 +03:00
• c02e390c2b viz: encode flops, mem and metadata in json (#16032) qazalandGitHub 2026-05-04 17:06:18 +03:00
• 4024d8438f runtime/graph: avoid core_id runtimevar merge conflicts (#16026) 3 people 2026-05-03 12:16:02 -04:00
• 9684334dfe viz: fix flops in graph, add null graph tracing (#16024) qazalandGitHub 2026-05-03 16:32:44 +03:00
• 419d525553 feat: handle multioutput kernel grads (#16028) wozeparrotandGitHub 2026-05-03 01:31:45 -04:00
• 9717d3a3a2 hotfix: prepend LD_LIBRARY_PATH to DLL posix search dirs (#16023) mefenglandGitHub 2026-05-03 01:45:19 +08:00
• 7daf4b7d52 viz: split cli test (#16015) qazalandGitHub 2026-05-02 19:47:11 +03:00
• d65b8ca25f jit: remove *input_list from the graph sources (#16021) nimlgenandGitHub 2026-05-02 14:42:47 +03:00
• 7dae9e6f7f viz: keep VIZ.value = 0 during python shutdown, cleanup launch (#16022) qazalandGitHub 2026-05-02 14:35:53 +03:00
• 637bdd5530 am: only support CDNA3/4 and RDNA3/4 (#16017) sirhcmandGitHub 2026-05-01 21:02:14 -07:00
• c0c120bf58 cleanups gate-on-load-store geohot 2026-05-01 23:52:45 +00:00
• 9596d13550 move gate to load/store geohot 2026-05-01 23:37:31 +00:00
• 4a2e1f1076 STORE doesn't have ranges anymore (#16019) George HotzandGitHub 2026-05-01 15:00:27 -07:00
• 0bffbc5f8a onnx fmod uses fmod (#16018) chenyuandGitHub 2026-05-01 16:47:11 -04:00
• 782d1ff80f Tensor.fmod (#16014) chenyuandGitHub 2026-05-01 16:02:18 -04:00
• 1079441332 revoke bus master (#16007) nimlgenandGitHub 2026-05-01 18:00:01 +03:00
• 8b147a9ed5 minimal repro for llama copies 2 (#16011) qazalandGitHub 2026-05-01 16:23:47 +03:00
• a29dd7b19b Revert "cleanup: untrack wait Metal buffers (#15954)" (#16010) qazalandGitHub 2026-05-01 15:18:19 +03:00
• 65879fe1b7 metal synchronize regression test (#16008) qazalandGitHub 2026-05-01 14:10:57 +03:00
• f6d92b55e6 am: use per pipe reset for gfx11+ (#16006) nimlgenandGitHub 2026-05-01 12:56:43 +03:00
• cee73becbe am: ip offsets in autogen (#16003) sirhcmandGitHub 2026-04-30 21:13:52 -07:00
• 4506688285 split render to render.py (#16002) George HotzandGitHub 2026-04-30 19:41:14 -07:00
• d651b4bbf0 SPEC=3 checks the shape (#16001) George HotzandGitHub 2026-04-30 18:41:37 -07:00
• 528d35e306 llama speed 4 (#15993) wozeparrotandGitHub 2026-05-01 08:14:41 +08:00
• 45fd7a3668 lil_image vectorize (#16000) George HotzandGitHub 2026-04-30 16:12:43 -07:00
• 81dccc51e2 stack image_refactors_stack geohot 2026-04-30 15:38:31 -07:00
• 55a7e4e6aa lil image refactors + vectorize->stack geohot 2026-04-30 15:36:04 -07:00
• eddcd4723b am_smi throttle info (#15997) wozeparrotandGitHub 2026-05-01 06:28:32 +08:00
• 03daefc625 changes image_idx_xy geohot 2026-04-30 22:25:09 +00:00
• fc68fcafa5 image index_x index_y geohot 2026-04-30 22:13:06 +00:00
• 52c92e15ae no replacement multinomial (#15995) chenyuandGitHub 2026-04-30 17:35:26 -04:00
• 8548d97306 handle contig on after contig_on_after geohot 2026-04-30 21:13:54 +00:00
• 0b389b23c8 remove custom kernel contiguous remove_ck_contig geohot 2026-04-30 13:18:32 -07:00
• cc21351428 move to SPEC=3 dtype_shape geohot 2026-04-30 12:42:33 -07:00
• 7e329c5219 spec=2 checks shape geohot 2026-04-30 11:39:34 -07:00
• d1193c72ac real fixes geohot 2026-04-30 11:12:40 -07:00
• e0b09f288f input validation for rand functions (#15990) chenyuandGitHub 2026-04-30 14:00:44 -04:00
• fe2dcbd573 fix image dtypes geohot 2026-04-30 10:58:41 -07:00
• 4b16c81944 Merge branch 'master' into dtype_shape George HotzandGitHub 2026-04-30 10:35:32 -07:00
• 11e1a2b89f cleaner and faster run_linear (#15987) nimlgenandGitHub 2026-04-30 20:15:22 +03:00
• 58b34e71bd failing test for llama useless copies (#15989) qazalandGitHub 2026-04-30 18:55:29 +03:00
• 05638ed496 Merge branch 'master' into dtype_shape George HotzandGitHub 2026-04-30 08:05:42 -07:00
• 0f7e296f5b fix some indexing edge cases (#15988) George HotzandGitHub 2026-04-30 08:05:30 -07:00
• f8460c1021 fix image geohot 2026-04-30 07:37:40 -07:00
• 273e0a4fa6 test fix geohot 2026-04-30 07:31:06 -07:00
• 649cdbf216 Merge branch 'master' into dtype_shape George HotzandGitHub 2026-04-30 07:24:10 -07:00
• 7969b205dd fix geohot 2026-04-30 07:22:06 -07:00
• ac6dee758a fix test geohot 2026-04-30 07:06:48 -07:00
• 4fb29cc0c4 const assert geohot 2026-04-30 07:02:54 -07:00
• c4d1792edf fixes geohot 2026-04-30 06:33:00 -07:00
• 4a4455f5b1 rev geohot 2026-04-30 06:30:28 -07:00
• 6f8b10d251 remove base Runner (#15986) nimlgenandGitHub 2026-04-30 13:04:55 +03:00
• 29dd605a91 Merge branch 'master' into dtype_shape George HotzandGitHub 2026-04-29 19:41:10 -07:00
• 46a36a838a small dtype shapes fixups (#15984) George HotzandGitHub 2026-04-29 19:40:38 -07:00
• b73248958a minor rand cleanups (#15982) chenyuandGitHub 2026-04-29 22:22:29 -04:00
• 5325db3af6 direct buffer view geohot 2026-04-29 18:38:04 -07:00
• cfdff84df0 fixes geohot 2026-04-29 18:20:20 -07:00
• 4bf0c35300 correct for index geohot 2026-04-29 17:27:41 -07:00
• 8ad8249e06 tests pass geohot 2026-04-29 16:01:29 -07:00
• 95d04048b0 more shapes geohot 2026-04-29 15:57:47 -07:00
• d1f9ade9a0 DEFINE_VAR can also have shape geohot 2026-04-29 15:46:42 -07:00
• dd19cdc0cd more shape geohot 2026-04-29 15:31:30 -07:00
• 4b4cfc0d81 dtype.count is shape geohot 2026-04-29 15:07:37 -07:00
• f8a66639a6 junk renderers_use_shapes_2 geohot 2026-04-29 21:55:30 +00:00
• 0095b91ce6 fixes geohot 2026-04-29 21:46:08 +00:00
• 3e13225f62 switch the renderers to use shape instead of dtype.count geohot 2026-04-29 21:38:15 +00:00
• 53a28bafbd rand device seed to its own function (#15979) chenyuandGitHub 2026-04-29 17:21:40 -04:00
• d07741f1d7 am: look for firmware in /lib/firmware/amdgpu (#15974) sirhcmandGitHub 2026-04-29 14:15:09 -07:00
• c73e667fc0 remove if for precompiled programs (#15980) nimlgenandGitHub 2026-04-29 23:43:36 +03:00
• 5b8ff231cd Merge branch 'master' into remove_vec_3 remove_vec_3 George HotzandGitHub 2026-04-29 13:31:51 -07:00
• 55915584e5 viz: fix cfg for emulated amd on the null device (#15976) qazalandGitHub 2026-04-29 23:18:09 +03:00
• dfd2d07005 remove CompiledRunner (#15970) nimlgenandGitHub 2026-04-29 22:45:48 +03:00
• 0080489abe llama: use env vars (#15978) wozeparrotandGitHub 2026-04-30 03:37:15 +08:00
• a37b605523 remove arch from asm kernel class (#15977) qazalandGitHub 2026-04-29 21:39:52 +03:00
• 7a79c2948a DEV visible device filter supports hyphenated syntax (#15971) sirhcmandGitHub 2026-04-29 11:02:21 -07:00
• 6b9a45568c autogen: better version handling for llvm and libclang (#15975) sirhcmandGitHub 2026-04-29 11:01:33 -07:00
• 654e611a29 _bits_to_rand to mixin (#15972) chenyuandGitHub 2026-04-29 13:47:25 -04:00
• a448b47e9c Merge branch 'master' into remove_vec_3 George HotzandGitHub 2026-04-29 10:30:18 -07:00