nimlgen/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Activity
14,335 Commits 334 Branches 15 Tags
rewrite_rangeify2
Commit Graph
501 Commits
Author SHA1 Message Date
wozeparrotandGitHub 4a1f32977c gptoss: default GROUPED_MOE=1 (#17537) 2026-08-14 12:24:37 -07:00
wozeparrotandGitHub 849074f0db gptoss: use fa swa (#17522) 2026-08-13 10:39:22 -07:00
qazalandGitHub 04c271ac41 simplify digitalocean_mi350x (#17502) 
* simplify digitalocean_mi350x

* no hardcoded rocm path
 2026-08-12 16:00:04 +09:00
qazalandGitHub e1013a6356 llama: create dataset cache by default in dev_beam (#17500) 2026-08-12 15:03:39 +09:00
wozeparrotandGitHub f891f5ffd0 gptoss: route lm_head thru asm_gemm (#17497) 2026-08-11 18:32:50 -07:00
qazalandGitHub 22722ea2e7 llama: correct optim_dtype for mxfp4 (#17482) 2026-08-11 03:01:28 +09:00
qazalandGitHub 2821bd646f late loss.to("CPU") in llama (#17476) 
* late loss.to("CPU") in llama

* acc = 0
 2026-08-10 17:31:50 +09:00
qazalandGitHub 44f1f45cd5 llama: custom silu kernels (#17462) 
* start by copying the C

* uop kernel

* cleanup tests

* estimates is part of SPEC
 2026-08-10 16:43:01 +09:00
qazalandGitHub 9dd3b8402e default llama 8b to MXFP4=1 (#17465) 2026-08-09 00:13:32 +08:00
qazalandGitHub 9636dd1a25 test MXFP4 llama without hipcc (#17435) 
* test MXFP4 llama without hipcc

* first pythonpath then dev
 2026-08-06 17:31:40 +09:00
qazalandGitHub f993228b73 llama: accurate mxfp4 mfu (#17388) 
* llama: accurate mxfp4 mfu

* train_llama3 import
 2026-08-04 18:41:57 +09:00
qazalandGitHub be5f62d269 llama: refactor amax stuff and skip in fp4 (#17375) 2026-08-03 20:05:52 +09:00
wozeparrotandGitHub e14cadb1fb gptoss: set ASM_GEMM (#17363) 2026-08-02 06:52:36 -07:00
wozeparrotandGitHub 98b700bad1 gptoss optim fixes (#17356) 2026-08-01 09:10:06 -07:00
wozeparrotandGitHub 4f5cadd15d gptoss ci (#17325) 2026-07-31 05:51:58 -07:00
wozeparrotandGitHub 93b74c75fc gptoss: grouped moe (#17322) 2026-07-31 03:25:32 -07:00
qazalandGitHub f7964acb64 llama with MXFP4 (#17321) 
* mxfp4 in llama

* less

* name
 2026-07-31 18:25:25 +09:00
wozeparrotandGitHub b5a2a5666a gptoss moe routing (#17284) 2026-07-30 07:49:14 -07:00
George HotzandGitHub 57ae1bc7a7 rename MULTI to UNSHARD (#17267) 
* rename MULTI to UNSHARD

* comment updates (glm)

* rename method to unshard
 2026-07-28 16:51:41 -07:00
George HotzGitHubteeny-runner
 		755dfb243b rename CPU_COUNT to NUM_CPU_THREADS with cgroup awareness (#17263) 
Rename CPU_COUNT to NUM_CPU_THREADS so it can be overridden via env var.
Default uses _get_cpu_count() which respects cgroup limits:
  - os.process_cpu_count() on Python 3.13+
  - /sys/fs/cgroup/cpu.max on cgroup v2
  - /sys/fs/cgroup/cpu/cpu.cfs_quota_us on cgroup v1
  - os.sched_getaffinity(0) fallback

Use NUM_CPU_THREADS.value in the dataloader instead of cpu_count(),
and update export_model.py and all renderer references.

Co-authored-by: teeny-runner <runner@teeny>
 2026-07-28 15:33:57 -07:00
wozeparrotandGitHub 056974468e gptoss: split no-wd params (#17233) 2026-07-27 02:58:43 -07:00
wozeparrotandGitHub f0117e98df refactor mlperf optim (#17200) 2026-07-25 10:37:11 -07:00
wozeparrotandGitHub 2e7db75668 gptoss: faster swa (#17150) 2026-07-23 06:56:27 -07:00
wozeparrotandGitHub 5f2eaeee40 gptoss: rope freqs in fp32 (#17132) 2026-07-22 06:11:06 -07:00
qazalandGitHub 1cf8f2f68c llama: inplace amax update (#17064) 
* llama: inplace amax update

* remove amax_out return

* work

* fit

* work

* work

* keep

* diff cleanup
 2026-07-20 15:05:41 +09:00
wozeparrotandGitHub ee290b3e39 optim: mxfp8 zero 1 allgathers in fp8 (#17073) 2026-07-18 07:44:50 -07:00
wozeparrotandGitHub a836c3822a gptoss: 3d mx block scale (#17062) 2026-07-16 23:30:24 -07:00
wozeparrotandGitHub 0d30f97584 mlperf: make v6.1 dir (#17031) 2026-07-15 10:40:55 -07:00
wozeparrotandGitHub 06169f5013 gptoss: small fixes (#17025) 2026-07-14 20:40:23 -07:00
qazalandGitHub 939f28d571 fused qkv rope custom kernel (#17021) 
* work

* fused qkv_norm

* work

* speed

* not that yet

* test cleanup

* just clone

* remove .realize()

* cleanup tests
 2026-07-15 01:08:42 +09:00
qazalandGitHub edfef062ed skip viz.cli -t in null device (#17018) 2026-07-14 19:24:58 +09:00
qazalandGitHub cae6696d75 llama: split current and next amax state (#16993) 2026-07-12 18:52:33 +09:00
wozeparrotandGitHub 5cc31e23e6 gptoss: scripts (#16962) 2026-07-09 20:50:20 -07:00
George HotzandGitHub fdffc6c0c8 remove dtypes base (#16931) 
* remove dtypes base

* find/replace bug

* vcount is junk too
 2026-07-08 11:48:11 -07:00
wozeparrotandGitHub ab131c2086 gptoss: zero-1 optim (#16916) 2026-07-07 18:34:47 -07:00
wozeparrotandGitHub a805ce03b1 gptoss: model train (#16884) 2026-07-06 22:07:50 -07:00
wozeparrotandGitHub a330bfffc9 gptoss: remove contiguous (#16882) 2026-07-05 17:48:32 -07:00
wozeparrotandGitHub 35522af0df gptoss: use quantize_mxfp8 (#16881) 2026-07-05 17:48:24 -07:00
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 42be177ea8 gpt-oss-20b: model (#16837) 
* feat: gpt-oss model file

* clean: don't need that function

* feat: working model
 2026-07-03 01:29:56 -07:00
chenyuandGitHub 36c0e81979 deprecate Tensor.training [PR] (#16774) 2026-06-27 11:02:28 -04:00
qazalandGitHub cb9df8bd33 fix profile.sh BENCHMARK=3 exit status (#16736) 2026-06-25 13:41:03 +09:00
qazalandGitHub 535c806c9f llama: profile.sh BENCHMARK=3 (#16722) 2026-06-24 19:20:51 +09:00
wozeparrotandGitHub dfea9e7994 llama: fused silu mul quantize mxfp8 (#16704) 2026-06-23 16:59:50 -07:00
chenyuandGitHub 33b635d23a Tensor.train -> TRAINING [PR] (#16705) 
* Tensor.train -> TRAINING [PR]

* doc
 2026-06-22 15:13:22 -04:00
wozeparrotandGitHub fe9b19b12d llama: more mp mem fixes (#16701) 
* llama: more mp mem fixes

* clean: unused

* fix: batch
 2026-06-22 10:54:35 -04:00
wozeparrotandGitHub 70cac72781 llama: realize weight init (#16623) 2026-06-15 23:00:19 -07:00
qazalandGitHub f998b9930a fp8 gemm inv_scale in epilogue (#16625) 
* fuse scale

* remove python inv_scale

* more inv_scale removal

* more cleanups

* cleaner

* diff polish

* work

* rename

* simpler

* simpler

* compute

* c

* Revert "c"

This reverts commit 8941fec7ca.

* Revert "compute"

This reverts commit 9db573a6d3.

* Revert "simpler"

This reverts commit 910ad33f87.

* Revert "simpler"

This reverts commit bf75d235a1.

* s_g

* update types

* less diff noise

* remove
 2026-06-15 18:44:41 +09:00
qazalandGitHub 4d34590b7d llama: less E kernels (#16517) 2026-06-12 19:49:25 +09:00
wozeparrotandGitHub e770805d21 llama: mxfp8 (#16574) 2026-06-11 22:15:24 -07:00