Hubert Lu a55a82302b [AMD] Fix ROCm FP8 dtype selection and MFMA support on gfx942/gfx950 (#1743) ...

* Fix gfx950 FP8 E4M3 selection

* Support FP8 E5M2 through BF8 MFMA intrinsics

* Use determine_fp8_type and determine_torch_fp8_type instead

2026-01-29 12:07:30 +08:00

..

amd

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

analysis

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

arith

[Refactor] Unify @jit and @lazy_jit into a single @jit decorator (#1632)

2026-01-09 15:41:39 +08:00

autotune

[Bugfix] Open Rocm ci test and fix some bugs. (#1443)

2026-01-06 02:18:29 +08:00

cache

[Bugfix] Open Rocm ci test and fix some bugs. (#1443)

2026-01-06 02:18:29 +08:00

carver

[Bugfix] Open Rocm ci test and fix some bugs. (#1443)

2026-01-06 02:18:29 +08:00

components

[Bugfix] Open Rocm ci test and fix some bugs. (#1443)

2026-01-06 02:18:29 +08:00

cpu

[Refactor] Phaseout execution_backend ctypes (#1510)

2025-12-23 19:52:16 +08:00

debug

[Bugfix] Open Rocm ci test and fix some bugs. (#1443)

2026-01-06 02:18:29 +08:00

fastmath

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

issue

[Layout] Fix Layout Bugs in Parallel and Reduce (#1713)

2026-01-28 10:56:25 +08:00

jit

[Refactor] Enhance T.alloc_barrier with new features and deprecate legacy mbarrier related intrinsics (#1733)

2026-01-28 15:20:13 +08:00

kernel

[Refactor] Unify @jit and @lazy_jit into a single @jit decorator (#1632)

2026-01-09 15:41:39 +08:00

language

[BugFix] Fix FP4 related vectorized cast (#1741)

2026-01-27 20:54:40 +08:00

layout

[EagerJIT] Add Support for Parameter Only Kernel Compilation (#1664)

2026-01-13 16:22:49 +08:00

math

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

metal

[tvm-ffi] Enable tvm-ffi for metal backend (#1289)

2026-01-19 13:46:03 +08:00

profiler

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

runtime

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

tilelibrary

[AMD] Fix ROCm FP8 dtype selection and MFMA support on gfx942/gfx950 (#1743)

2026-01-29 12:07:30 +08:00

transform

[Refactor] Enhance T.alloc_barrier with new features and deprecate legacy mbarrier related intrinsics (#1733)

2026-01-28 15:20:13 +08:00

utils

[Lint] Phaseout Yapf format and embrace ruff format (#1417)

2025-12-12 17:22:18 +08:00

webgpu

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00