Skip to content

Pull requests: tinygrad/tinygrad

New pull request New
103 Open 13,775 Closed
103 Open 13,775 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

buffer view is like buffer
#15082 opened Mar 2, 2026 by geohot Loading…
1
symbolic llm with prefill (ai slop)
#15080 opened Mar 2, 2026 by geohot Loading…
1
add gpu_family detection to Metal, target MSL 4.0 on macOS 26+
#15079 opened Mar 1, 2026 by valtterivalo Loading…
1
feat: package extra as tinygrad.extra
#15078 opened Mar 1, 2026 by ionodeionode Loading…
1
add Tensor.associative_scan for parallel prefix scans
#15075 opened Mar 1, 2026 by adityasugandhi Loading…
1
1
fa: change bwd grid dim + unshuffle using mops
#15068 opened Feb 28, 2026 by wozeparrot Loading…
viz: show sqtt INST packets in program context
#15065 opened Feb 28, 2026 by Qazalin • Draft
1
include optimization env vars in beam cache key
#15057 opened Feb 28, 2026 by adityasugandhi Loading…
1
1
use Buffer.view() sub-buffers in gguf_load for kernel dedup
#15052 opened Feb 27, 2026 by man7iss Loading…
1
add RDNA2 (gfx1030) emulator support
#15043 opened Feb 27, 2026 by Zaneham • Draft
4
onnx no longer needs is_dtype_supported [skip_process_replay]
#15017 opened Feb 25, 2026 by sirhcm Loading…
1
strixhalo bench
#15016 opened Feb 25, 2026 by nimlgen Loading…
1
clang: map bfloat16 to unsigned short for portability
#15004 opened Feb 25, 2026 by altis0725 Loading…
6 tasks done
1
1
asm_gemm: support more sharding
#15002 opened Feb 25, 2026 by wozeparrot • Draft
embedded bwd vocab shard
#15001 opened Feb 25, 2026 by wozeparrot Loading…
1
llama3: mp + sum_dtype
#15000 opened Feb 25, 2026 by wozeparrot Loading…
cast to larger dtype moves after bufferize
#14995 opened Feb 25, 2026 by sirhcm • Draft
1
am: thm
#14985 opened Feb 24, 2026 by nimlgen • Draft
1
cdna4: cleanup with fast attention and gemm support
#14984 opened Feb 24, 2026 by npinto Loading…
1
assembly/amd: v_cmp_lg_f32 is ordered not-equal
#14982 opened Feb 24, 2026 by b1tg Loading…
1
Cache graph traversal results [pr]
#14957 opened Feb 23, 2026 by Laserbear Loading…
1
one run_schedule in realize
#14955 opened Feb 22, 2026 by chenyuxyz • Draft
1
add fp8 fnuz dtypes with PYTHON backend support
#14945 opened Feb 21, 2026 by b1tg Loading…
6
Cdna VIZ=2 at least runs
#14917 opened Feb 20, 2026 by kevvz • Draft
2
amd/cdna4: cleanup + gemm/fa tests bounty locked Bounty is locked to someone
#14914 opened Feb 20, 2026 by hurrrsh Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.