Skip to content

Actions: pytorch/ao

Actions

Claude Code

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
claude-code.yml
564 workflow runs
564 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Passing alg_id by semi sparse config (#4180) Claude Code #540: Issue comment #4180 (comment) created by RandySheriff
1s
1s
add torch.compile to blockwise quantized kernel unit tests Claude Code #539: Issue comment #4187 (comment) created by pytorch-bot bot
1s
1s
fix undefined values for tail elements in act quant kernels Claude Code #538: Issue comment #4186 (comment) created by pytorch-bot bot
2s
2s
Passing alg_id by semi sparse config (#4180) Claude Code #537: Issue comment #4180 (comment) created by jerryzh168
2s
2s
Support 32x32 scaling for weights in MXFP8 weight quantization kernel Claude Code #536: Issue #4185 opened by danielvegamyhre
1s
1s
fuse dynamic per group padding into cutedsl 2d MXFP8 quantization kernel Claude Code #535: Issue #4184 opened by danielvegamyhre
1s
1s
CUDA -> Helion exploration for token group padding/unpadding kernels Claude Code #534: Issue comment #4062 (comment) created by danielvegamyhre
2s
2s
Triton -> CuteDSL dim0 quantization kernel with RCEIL scaling that writes scales directly to ((32,4),4) layout for tcgen05 mma Claude Code #533: Issue comment #4052 (comment) created by danielvegamyhre
1s
1s
add rope fusion detection tests Claude Code #532: Issue comment #4183 (comment) created by pytorch-bot bot
1s
1s
Passing alg_id by semi sparse config (#4180) Claude Code #531: Issue comment #4180 (comment) created by RandySheriff
1s
1s
support Per Group in Float8DynamicActivationFloat8WeightConfig (#4182) Claude Code #530: Issue comment #4182 (comment) created by zlin888
2s
2s
Passing alg_id by semi sparse config (#4180) Claude Code #529: Issue comment #4180 (comment) created by jerryzh168
1s
1s
support Per Group in Float8DynamicActivationFloat8WeightConfig (#4182) Claude Code #528: Issue comment #4182 (comment) created by meta-codesync bot
2s
2s
support Per Group in Float8DynamicActivationFloat8WeightConfig (#4182) Claude Code #527: Issue comment #4182 (comment) created by pytorch-bot bot
10s
10s
Add fused FP8 rowwise scale+cast kernel for MoE forward pass Claude Code #526: Issue comment #3973 (comment) created by danielvegamyhre
1s
1s
Prevent folding of mutable input to copy_ and put_ operators Claude Code #525: Issue comment #4181 (comment) created by tom-arm
1s
1s
Prevent folding of mutable input to copy_ and put_ operators Claude Code #524: Issue comment #4181 (comment) created by pytorch-bot bot
2s
2s
Add CodeML'25 BibTeX Claude Code #523: Issue comment #3978 (comment) created by namgyu-youn
1s
1s
[X86] Enable FP8 qlinear patterns for AOT Inductor Claude Code #522: Issue comment #4099 (comment) created by meta-cla bot
1s
1s
x86 SDPA support qkv-fused input Claude Code #521: Issue comment #3986 (comment) created by meta-cla bot
1s
1s
x86 SDPA support qkv-fused input Claude Code #520: Issue comment #3986 (comment) created by meta-cla bot
1s
1s
Add WAN style rope detection pattern for low precision attention API Claude Code #519: Issue comment #4173 (comment) created by howardzhang-cv
1s
1s
Fix aten._has_compatible_shallow_copy_type', overload='default' dispatcher failed for LinearActivationQuantizedTensor in inference mode Claude Code #518: Issue comment #4098 (comment) created by xiaowangintel
2s
2s
Fix aten._has_compatible_shallow_copy_type', overload='default' dispatcher failed for LinearActivationQuantizedTensor in inference mode Claude Code #517: Issue comment #4098 (comment) created by xiaowangintel
1s
1s
aten._has_compatible_shallow_copy_type', overload='default' dispatcher failed for LinearActivationQuantizedTensor in inference mode Claude Code #516: Issue comment #4097 (comment) created by xiaowangintel
1s
1s