Skip to content

Actions: NVIDIA/TransformerEngine

Actions

Lint

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
lint.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[fused_router][pytorch] Optimize naive topk path and add perf benchmark Lint #18084: Pull request #2776 synchronize by XiaomingFun233
Action required XiaomingFun233:pr/fused-router-topk-opt
XiaomingFun233:pr/fused-router-topk-opt
Action required
Optimize function that loads pointers on GPU Lint #18083: Pull request #3001 synchronize by timmoon10
2m 3s timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
2m 3s
Optimize function that loads pointers on GPU Lint #18082: Pull request #3001 synchronize by pre-commit-ci Bot
2m 22s timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
2m 22s
Optimize function that loads pointers on GPU Lint #18081: Pull request #3001 synchronize by timmoon10
1m 7s timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
1m 7s
[Common] Comm+GEMM overlap API updated to support cuBlasMp backend (incl. framework API) Lint #18080: Pull request #2443 synchronize by pre-commit-ci Bot
2m 4s denera:common/tp-overlap-cublasmp
denera:common/tp-overlap-cublasmp
2m 4s
[Common] Comm+GEMM overlap API updated to support cuBlasMp backend (incl. framework API) Lint #18079: Pull request #2443 synchronize by denera
2m 5s denera:common/tp-overlap-cublasmp
denera:common/tp-overlap-cublasmp
2m 5s
[PyT] Reduce test sizes in fused attn fp8 vs fp16 to avoid OOM Lint #18078: Pull request #3020 synchronize by vedaanta
2m 4s vedaanta:vedaanta/te-fp8-vs-f16-shrink-b1
vedaanta:vedaanta/te-fp8-vs-f16-shrink-b1
2m 4s
Bitmap topk Lint #18077: Pull request #3009 synchronize by tdophung
2m 20s tdophung:bitmap_topk
tdophung:bitmap_topk
2m 20s
Add the getter and setter of skip_fp8_weight_update_tensor Lint #18076: Pull request #3015 synchronize by xrennvidia
2m 31s xrennvidia:xren/fix_skip_fp8_weight_update
xrennvidia:xren/fix_skip_fp8_weight_update
2m 31s
Bitmap topk Lint #18075: Pull request #3009 synchronize by pre-commit-ci Bot
2m 27s tdophung:bitmap_topk
tdophung:bitmap_topk
2m 27s
Bitmap topk Lint #18074: Pull request #3009 synchronize by tdophung
1m 8s tdophung:bitmap_topk
tdophung:bitmap_topk
1m 8s
Optimize function that loads pointers on GPU Lint #18073: Pull request #3001 synchronize by timmoon10
2m 6s timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
2m 6s
Optimize function that loads pointers on GPU Lint #18072: Pull request #3001 synchronize by timmoon10
2m 5s timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
timmoon10:tmoon/optimize-get_device_pointer_for_data_and_scales
2m 5s
Add wheel support for Newton-Schulz method via cuSolverMp Lint #18071: Pull request #3004 synchronize by ksivaman
2m 5s ksivaman:expand_wheel_builds
ksivaman:expand_wheel_builds
2m 5s
Add NVFP4 per-token quantization recipe Lint #18070: Pull request #3045 synchronize by pre-commit-ci Bot
Action required cael-ling:feature/nvfp4-per-token-recipe
cael-ling:feature/nvfp4-per-token-recipe
Action required
Add NVFP4 per-token quantization recipe Lint #18069: Pull request #3045 opened by cael-ling
Action required cael-ling:feature/nvfp4-per-token-recipe
cael-ling:feature/nvfp4-per-token-recipe
Action required
[PyTorch Debug] Add scale_inv_std stat and skip NVFP4 layers in LogFp8TensorStats Lint #18068: Pull request #3044 synchronize by pre-commit-ci Bot
2m 22s pggPL:debug_log_fp_fixes
pggPL:debug_log_fp_fixes
2m 22s
[PyTorch Debug] Add scale_inv_std stat and skip NVFP4 layers in LogFp8TensorStats Lint #18067: Pull request #3044 opened by pggPL
1m 9s pggPL:debug_log_fp_fixes
pggPL:debug_log_fp_fixes
1m 9s
[PyTorch] Make modules.GroupedLinear graph-safe Lint #18066: Pull request #3038 synchronize by yaox12
2m 5s yaox12:xiny/enable-grouped-quantize-cublaslt
yaox12:xiny/enable-grouped-quantize-cublaslt
2m 5s
docs: expand comm gemm overlap guidance Lint #18065: Pull request #3043 synchronize by omribz156
Action required omribz156:codex/comm-gemm-overlap-docs
omribz156:codex/comm-gemm-overlap-docs
Action required
docs: expand comm gemm overlap guidance Lint #18064: Pull request #3043 opened by omribz156
Action required omribz156:codex/comm-gemm-overlap-docs
omribz156:codex/comm-gemm-overlap-docs
Action required
Use cuDNN for row-scaled NVFP4 grouped GEMM Lint #18063: Pull request #3042 opened by zianglih
Action required zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
Action required
Generalized Tensor Parallelism (GTP) Lint #18062: Pull request #3005 synchronize by fanshiqing
2m 1s fanshiqing:gtp_release
fanshiqing:gtp_release
2m 1s
[common] Grouped gemm update - nvfp4 for blackwell and fp8 blockwise hopper Lint #18061: Pull request #2971 synchronize by pggPL
2m 8s pggPL:grouped_gemm_nvfp4_and_hopper
pggPL:grouped_gemm_nvfp4_and_hopper
2m 8s
Generalized Tensor Parallelism (GTP) Lint #18060: Pull request #3005 synchronize by pre-commit-ci Bot
2m 20s fanshiqing:gtp_release
fanshiqing:gtp_release
2m 20s