sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions Activity
14,537 Commits 336 Branches 15 Tags
explicit-dev
Commit Graph
37 Commits
Author SHA1 Message Date
George HotzandGitHub 625c05df1e fix am_smi to respect dev (#17742) 2026-08-25 19:21:55 -07:00
qazalandGitHub a1263fadf3 fused_qkv_rope in UOp try 2 (#17619) 
* fused_qkv_rope in UOp try 2

* dont need that

* less
 2026-08-20 12:28:34 +09:00
qazalandGitHub d539aaf752 Revert "fused_qkv_rope in UOp (#17591)" (#17593) 
This reverts commit 8c2bf02d17.
 2026-08-19 21:42:55 +09:00
qazalandGitHub 8c2bf02d17 fused_qkv_rope in UOp (#17591) 
* llama: 4% faster fused_qkv_rope

* prep

* add uop kernel, has_hipcc is cached

* less
 2026-08-19 18:07:30 +09:00
qazalandGitHub f258708d7d llama: custom quantize_mxfp4+transpose kernel (codex) (#17434) 
* llama: custom quantize_mxfp4+transpose kernel (codex)

* rename to cpp

* inline

* cleanup

* lds load_bf16x4

* more tests, add Estimates
 2026-08-06 16:13:28 +09:00
qazalandGitHub 0a3325f9c2 add mxfp4 quantize and layout kernels (#17320) 2026-07-31 14:50:18 +09:00
qazalandGitHub a8c1e89500 fp4 asm gemm 6+ pflops (#17315) 
* fp4 gemm

* better kernargs structure

* move to .s files

* work

* work

* p2

* style

* use .py

* move to dsl

* cleanup

* add MFMA_SCALE_X2_ENCODING

* cleanup mfma

* fma docs

* gemm_mxfp4

* more cleanup

* move

* move to cdna_asm_gemm

* change

* rm

* change

* mx
 2026-07-31 14:25:23 +09:00
qazalandGitHub cae6696d75 llama: split current and next amax state (#16993) 2026-07-12 18:52:33 +09:00
qazalandGitHub 75a4bfddc9 fp8 gemm tests including fused scales (#16980) 
* fp8 gemm tests matching fused scales

* work

* diff
 2026-07-11 12:33:21 +09:00
qazalandGitHub bc3bf1988a asm gemm test cleanups try 2 (#16964) 
* fix hipcc requirement

* move hipcc

* fp8 in llama

* update some of those skips

* update dtype

* change
 2026-07-10 16:00:24 +09:00
qazalandGitHub 07f7383d29 llama: remove unused bf16 assembly gemm (#16859) 
* only hk bf16 gemm

* rm asm gemm

* more cleanup

* half isn't supported in asm gemm anymore

* more test edits

* unused

* remove TestMagicGu

* uop gemm is still tested

* minimal diff
 2026-07-04 18:41:54 +09:00
wozeparrotandGitHub bba611bb59 gemm: fix mxfp8 on more shapes (#16677) 2026-06-19 13:28:53 -07:00
wozeparrotandGitHub 36f6d1b064 gemm: fix bf16 atb for mp sharding (#16637) 2026-06-16 15:58:47 -07:00
wozeparrotandGitHub c38d6a7e3a mxfp8 part 2 (#16561) 2026-06-10 23:36:11 -07:00
wozeparrotandGitHub 2bdc360606 gemm: mxfp8 hipkittens gemm (#16541) 
* gemm: mxfp8 hipkittens gemm

* feat: update hipkittens

* feat: kernel signature

* clean: just kernel

* feat: from tinygrad

* feat: test

* fix: add back utils

* clean: no diff

* clean: no diff
 2026-06-09 15:20:05 -07:00
sirhcmandGitHub 172f9493e1 move is_dtype_supported to renderer (#16226) 2026-05-20 21:19:37 -04:00
chenyuandGitHub 8631b6f17d remove use of requires_grad in test/ (#16237) 2026-05-16 17:21:07 -04:00
chenyuandGitHub 0ddc50d050 do not gate backward on requires_grad (#16230) 
DETACH is filtered in _deepwalk. instead of None, it gets 0 grad now
 2026-05-16 12:29:49 -04:00
qazalandGitHub ebcb7b7cc0 fp8 gemm tests with scale args (#16231) 
* update atol

* update fp8 path

* more work

* update profile.sh
 2026-05-16 20:47:58 +09:00
chenyuandGitHub 409bb0c9ad requires_grad cannot be None (#16212) 
final goal is to remove requires_grad, first change the default to True, and don't allow None
 2026-05-15 02:01:04 -04:00
chenyuandGitHub 7a1adfd2aa update Tensor.allclose to return Tensor (#15904) 
matches jax
 2026-04-24 08:27:17 -04:00
sirhcmandGitHub 6adf4c3cd9 MOCKGPU interfaces (#15796) 2026-04-17 21:56:29 -04:00
qazalandGitHub 39a029ec55 remove ASM_GEMM context var (#15645) 2026-04-08 18:02:40 +09:00
wozeparrotandGitHub 70dbd35023 llama: move custom_kernel into flat_llama (#15643) 2026-04-08 00:19:14 -07:00
wozeparrotGitHubqazal
 		7e54992bf6 fp8 llama (#15588) 
Co-authored-by: qazal <[email protected]>
 2026-04-04 18:24:57 -07:00
sirhcmGitHubComma Device
 		645d45d968 DEV has arch (#15577) 
Co-authored-by: Comma Device <[email protected]>
 2026-04-03 19:17:19 -04:00
sirhcmandGitHub 0ed8d9271d Renderers accept Target or nothing (#15590) 2026-04-03 01:09:41 -04:00
qazalandGitHub fefb0ebc2a gemm/asm: fp8 cleanups (#15580) 
* normal gemm here

* s/dtypes.fp8e4m3/FP8_DTYPE

* gemm_bw

* device UOp stays NULL
 2026-04-02 19:02:38 +09:00
qazalandGitHub 8feb8edc68 gemm/asm: add fp8 support to cdna asm_gemm (#15542) 
* work

* hmm, mixins

* rhs_transposed

* also fix the dtype

* check for hipcc

* Exception

* select dev

* default
 2026-03-31 19:32:54 +09:00
qazalandGitHub f88e255cea gemm/asm: split and parameterize dtype in llama gemm tests (#15408) 
* gemm/asm: more tests for emulator, parameterize llama gemm tests

* bf16 atol
 2026-03-31 17:12:44 +09:00
sirhcmandGitHub bc180a963c deprecate <dev>=1 in favor of DEV=<dev> (#15467) 
* start work on target

* add test

* update actions to use DEV

* update docs

* update readmes

* tests need that too

* update example

* update tests (comments)

* fix that test

* ruff

* mypy

* oops

* remove getenvs

* don't add Target yet

* and the test

* lint

* and docs

* more stuff

* assert

* few more fixes

* test assert
 2026-03-26 03:48:03 -04:00
qazalGitHubgeohotGeorge Hotz
 		176ad47d7d cdna4 emulator testing ASM_GEMM in CI (#15373) 
* cdna emulator work

* accvgprs

* cdna passes most tests

* ruff

* add cdna4 to tests

* cdna emu

* crash

* pass?

* work

* gen

* clean up wave_size access

* asm_gemm passes

* remove acc from dsl.py, emulator can keep its different reg file

it's purely an encoding here, the ASM_GEMM already encodes acc srcs with v[], this can
be cleaned up later, but not functionally required for emulator.

* split asm_gemm tests to ones fast on the emulator

* don't do that

* 124 stays null on rdna

* the segfault was because of hw regs, not this

* Revert "clean up wave_size access", it's explicitly tested

This reverts commit 1202ff5787.

* nullcopyout

---------

Co-authored-by: George Hotz <[email protected]>
Co-authored-by: George Hotz <[email protected]>
 2026-03-20 05:51:30 +09:00
qazalandGitHub 33bd33e783 sqtt: add CDNA ops enum, show in viz (#15140) 2026-03-17 09:38:42 +09:00
qazalandGitHub 5cd1daa3bc cdna asm_gemm in one file, remove old rdna3 asm (#15281) 2026-03-16 04:32:30 +09:00
wozeparrotandGitHub c35de9bd68 asm_gemm: support more sharding (#15002) 2026-03-02 23:16:37 -08:00
qazalandGitHub 5b6fcd1cda gemm/asm: smallest cdna4 asm gemm test (#14925) 2026-02-21 11:56:05 +09:00
qazalandGitHub f590564bf7 gemm multiple is only for cdna4 asm (#14814) 
* gemm multiple is only for cdna4 asm

* move to backend

* and arch

* path
 2026-02-17 14:00:02 +09:00