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

• b2caf4c2b3 prepare for custom kernel (#13029) George HotzandGitHub 2025-10-31 14:47:37 +08:00
• 564e9ccc31 fix show indexing toggle default on (#13030) qazalandGitHub 2025-10-31 14:41:15 +08:00
• 6cd341354e viz: add toggle to hide indexing UOps (#13027) qazalandGitHub 2025-10-31 13:21:11 +08:00
• b46229ca51 use shrink in amd_matmul_uop (#13026) George HotzandGitHub 2025-10-31 10:43:41 +08:00
• 78f7650eec faster tk matmul (#13006) wozeparrotandGitHub 2025-10-30 19:09:27 -07:00
• 512513c403 cleanup amd uop matmul (#13025) George HotzandGitHub 2025-10-31 10:04:45 +08:00
• e6806015a5 colors amd_uop_cleanups geohot 2025-10-31 09:57:23 +08:00
• 40af34f9ab render fallback geohot 2025-10-31 09:50:23 +08:00
• be3fad06f4 more geohot 2025-10-31 09:40:43 +08:00
• 540a11a850 var names geohot 2025-10-31 09:31:47 +08:00
• 0a4c77e85f better variable names geohot 2025-10-31 09:28:51 +08:00
• 2543ce7585 move that out geohot 2025-10-31 09:12:38 +08:00
• ba1d1142be remove mod geohot 2025-10-31 09:02:35 +08:00
• 59ad5d51f5 cleanup amd uop matmul geohot 2025-10-31 08:44:05 +08:00
• f6430a0559 add script for one slow openpilot conv (#12953) chenyuandGitHub 2025-10-30 18:08:41 -04:00
• 73002ebffa print p.applied_opts with DEBUG >= 3 (#13024) chenyuandGitHub 2025-10-30 16:51:21 -04:00
• 99e76f33a0 remove unneeded TYPE_CHECKING [pr] (#13020) chenyuandGitHub 2025-10-30 12:01:13 -04:00
• 629b177b66 amd: sqtt works in profile mode (#13019) nimlgenandGitHub 2025-10-30 23:48:52 +08:00
• 4c8362128b New symbolic renderer + strip parens (#13017) Sieds LyklesandGitHub 2025-10-30 16:41:32 +01:00
• c78dfcc5a1 simplify ProgramSpec __post_init__ STORE/LOAD [pr] (#13018) chenyuandGitHub 2025-10-30 11:13:21 -04:00
• 363a201cc6 fp8 amd cstyle (#12999) 3 people 2025-10-30 22:45:52 +08:00
• 5be3a93d02 amd: enable pmc on gfx12 (#13015) nimlgenandGitHub 2025-10-30 22:43:10 +08:00
• cf5ab93b8e amd: pmc grbm block (#13016) nimlgenandGitHub 2025-10-30 22:42:59 +08:00
• 4d7a7096c9 am: enable perfmon (#13013) nimlgenandGitHub 2025-10-30 22:28:36 +08:00
• 985b6eb95f ues less typing.cast [pr] (#13002) chenyuandGitHub 2025-10-30 09:29:52 -04:00
• 5eb87ab131 hotfix: bump cifar time to 350 geohot 2025-10-30 17:29:20 +08:00
• 4a741e8364 modernize amd uop matmul (#13011) George HotzandGitHub 2025-10-30 17:02:38 +08:00
• f0b9416432 Merge branch 'master' into amd_uop amd_uop George HotzandGitHub 2025-10-30 16:54:39 +08:00
• b1db99cefe format geohot 2025-10-30 16:53:21 +08:00
• de28eaa610 fix estimates geohot 2025-10-30 16:48:46 +08:00
• f3da3c9be5 mac cleanups geohot 2025-10-30 16:45:01 +08:00
• c43f22b143 revert that geohot 2025-10-30 16:35:33 +08:00
• 34e631eb26 more comments geohot 2025-10-30 08:24:26 +00:00
• 16983e9c95 comment geohot 2025-10-30 08:04:57 +00:00
• 66ea3a0be4 put DEFINE_LOCAL counter in context (#13008) qazalandGitHub 2025-10-30 15:49:26 +08:00
• 3eb00a421f progress geohot 2025-10-30 07:43:03 +00:00
• b54493b003 modernize amd uop matmul geohot 2025-10-30 07:10:00 +00:00
• e456f2cb1e more uop programs (#13007) George HotzandGitHub 2025-10-30 14:57:59 +08:00
• c18b283f58 feat: timeout on stuck socket (#13009) wozeparrotandGitHub 2025-10-29 23:11:26 -07:00
• 92a87e37e4 fix: fetch_file (#13010) wozeparrotandGitHub 2025-10-29 22:44:22 -07:00
• e64d4b3b44 uops programs (#13005) George HotzandGitHub 2025-10-30 12:28:10 +08:00
• 9d4e74a52a comments uop_prg geohot 2025-10-30 12:27:55 +08:00
• e887ad6317 more syntax geohot 2025-10-30 12:11:18 +08:00
• 98b76aa3aa more syntax geohot 2025-10-30 12:04:26 +08:00
• 2f80994ce8 Merge branch 'master' into uop_prg George HotzandGitHub 2025-10-30 11:22:36 +08:00
• 5894df059c hotfix: prevent inf loop if reduce splits geohot 2025-10-30 11:21:40 +08:00
• 2ef52db298 work geohot 2025-10-30 11:12:37 +08:00
• 80f9347e53 work geohot 2025-10-30 11:01:53 +08:00
• 79f98a6624 uops programs geohot 2025-10-30 10:52:44 +08:00
• 2da02f1ae1 add loads at the end (#12988) George HotzandGitHub 2025-10-30 10:42:19 +08:00
• 89d8b79196 fix more tests late_add_load geohot 2025-10-30 10:32:22 +08:00
• adc15c7497 fix abs2 geohot 2025-10-30 10:21:24 +08:00
• 56f4961f2f fix where on load geohot 2025-10-30 10:16:35 +08:00
• 54ffca78a7 spec test passes geohot 2025-10-30 10:09:56 +08:00
• 281761b494 fix matvec geohot 2025-10-30 09:59:25 +08:00
• 42726bcc29 tests passing geohot 2025-10-30 09:55:36 +08:00
• cd8272f129 late load geohot 2025-10-30 09:20:51 +08:00
• 2ef53a7a90 Merge branch 'master' into late_add_load George HotzandGitHub 2025-10-30 09:14:31 +08:00
• 4b001ec723 amd: pmc in mockgpu (#13000) nimlgenandGitHub 2025-10-30 01:52:02 +08:00
• a6f5b1482e amd: perf counters (#12975) nimlgenandGitHub 2025-10-30 00:10:31 +08:00
• 457602b350 fix fp8 cast folding (#12997) b1tgandGitHub 2025-10-29 21:27:42 +08:00
• 70bce62c67 dont collapse possibly empty symbolic range (#12994) Sieds LyklesandGitHub 2025-10-29 12:17:09 +01:00
• 3cfd4c915f warp_num demote_op geohot 2025-10-29 19:08:10 +08:00
• 79903ae2be refactor z3 renderer (#12996) Sieds LyklesandGitHub 2025-10-29 12:01:07 +01:00
• abb01ce6a0 last geohot 2025-10-29 18:57:38 +08:00
• 6853da2a2f works geohot 2025-10-29 18:45:16 +08:00
• 154ddd98fd it works, it's just slow... geohot 2025-10-29 18:35:44 +08:00
• e4ef94cf10 both is broken geohot 2025-10-29 18:15:38 +08:00
• 0c274151ad tensor core works geohot 2025-10-29 18:06:05 +08:00
• c4e32d4f63 demote op geohot 2025-10-29 17:47:12 +08:00
• a9d91ffcfc DEMOTE op for putting globals in locals geohot 2025-10-29 17:22:59 +08:00
• 819592ee67 hotfix: disable DoubleMatmul for PTX geohot 2025-10-29 16:37:17 +08:00
• 30ca3f2af8 all double matmul (#12993) George HotzandGitHub 2025-10-29 16:25:27 +08:00
• 9f39f6391c shared_codegen_spec and fix index spec (#12967) Sieds LyklesandGitHub 2025-10-29 09:14:11 +01:00
• 1c362736aa fix more double matmuls (#12991) George HotzandGitHub 2025-10-29 16:09:48 +08:00
• e42b4edf8c remove if stuff (#12992) George HotzandGitHub 2025-10-29 15:29:35 +08:00
• 8c47cf4323 pcontig double matmul works (#12899) George HotzandGitHub 2025-10-29 13:06:43 +08:00
• 35b6f4148d delete untested quantize (#12990) George HotzandGitHub 2025-10-29 12:46:32 +08:00
• e6d2cb68dd simpler geohot 2025-10-29 12:27:40 +08:00
• 5f65d37064 Merge branch 'master' into late_add_load George HotzandGitHub 2025-10-29 12:13:37 +08:00
• 801003ba95 add loads at the end geohot 2025-10-29 12:09:49 +08:00
• 5ce8a1d2f2 Merge adjacent try all permutations for reduce (#12972) Sieds LyklesandGitHub 2025-10-29 05:04:54 +01:00
• b147e7e8e6 flatten bufferize (#12984) George HotzandGitHub 2025-10-29 11:23:43 +08:00
• a7dac11aad viz: keep rewrite step in back button history (#12986) qazalandGitHub 2025-10-29 11:09:43 +08:00
• 37967fa17b viz: add integer query param helper and more typing (#12985) qazalandGitHub 2025-10-29 10:44:01 +08:00
• fb53bdad5d unused propagate_invalid rules [pr] (#12983) chenyuandGitHub 2025-10-28 22:16:50 -04:00
• ef16e6c68c unwrap instead of cast [pr] (#12982) chenyuandGitHub 2025-10-28 21:29:23 -04:00
• f55fcfecf9 ProgramSpec uops must end with SINK [pr] (#12981) chenyuandGitHub 2025-10-28 17:12:22 -04:00
• 9442442cb1 update variable names in search [pr] (#12979) chenyuandGitHub 2025-10-28 15:37:52 -04:00
• d66c997a39 feat: thunderkittens fa2 (#12955) wozeparrotandGitHub 2025-10-28 11:27:45 -07:00
• bb307b9e81 fix fp8 vectorization (#12977) b1tgandGitHub 2025-10-29 01:55:30 +08:00
• c11dd56956 amd: cleanup import urls (#12976) nimlgenandGitHub 2025-10-29 00:43:02 +08:00
• bb7aa19d67 Merge branch 'master' into replace_if_with_range replace_if_with_range George HotzandGitHub 2025-10-28 23:02:15 +08:00
• 5e01cc299b zero len ranges fail (#12974) George HotzandGitHub 2025-10-28 22:49:55 +08:00
• e936aa7974 cleanups from if range branch (#12973) George HotzandGitHub 2025-10-28 20:58:47 +08:00
• f55f488543 cleanups from if range branch if_range_cleanups geohot 2025-10-28 19:38:45 +08:00
• 117f37ae5f don't remove the gate geohot 2025-10-28 19:28:38 +08:00
• ba23b097c1 fix image geohot 2025-10-28 19:22:59 +08:00
• 3341272771 cleanup patterns geohot 2025-10-28 19:15:01 +08:00
• 975f5ccc99 tests pass geohot 2025-10-28 19:12:21 +08:00