Skip to content

Actions: EmbeddedLLM/aiter

Actions

Checks

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-checks.yaml
53 workflow runs
53 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
ci: make Aiter S3 wheel manifest cache-safe (#4807) Checks #53: Commit 6fcd8d4 pushed by BadrBasowid
53s main
main
53s
Optimize Opus MoE A8W4 stage2 candidates (#4152) Checks #52: Commit 79c896d pushed by big-yellow-duck
57s main
main
57s
fix the adress over 32bit and radom nan error (#3988) Checks #51: Commit 664a7b0 pushed by big-yellow-duck
51s main
main
51s
configs: add DSv4-Flash shape to dsv4_fp8fp4_tuned_fmoe.csv (#3214) Checks #50: Commit ce07928 pushed by big-yellow-duck
45s main
main
45s
CI: separate Aiter Test concurrency for push and schedule (#2718) Checks #49: Commit 655d944 pushed by big-yellow-duck
52s main
main
52s
So/a8w8 bpreshuffle flydsl (#2546) Checks #48: Commit 8d30ef5 pushed by big-yellow-duck
46s main
main
46s
[gfx1201] Enable RMSNorm support for gfx1201 Checks #47: Pull request #7 synchronize by big-yellow-duck
47s rdna4_rmsnorm-support
rdna4_rmsnorm-support
47s
[HIP] Refine split fused GDR decode test (#2446) Checks #46: Commit 4fc1787 pushed by big-yellow-duck
42s main
main
42s
[gfx1201] Enable RMSNorm support for gfx1201 Checks #45: Pull request #7 opened by big-yellow-duck
43s rdna4_rmsnorm-support
rdna4_rmsnorm-support
43s
[gfx1201] Enable quantization kernels for gfx12xx Checks #44: Pull request #6 opened by big-yellow-duck
45s rdna4_quant-support
rdna4_quant-support
45s
[gfx1201] Added tuned gemm_a8w8_configs for gfx1201 Checks #43: Pull request #5 opened by big-yellow-duck
57s rdna4_ck-gemm-a8ww8-blockscale
rdna4_ck-gemm-a8ww8-blockscale
57s
[OPUS] Add finfo class for float-valued type properties (#2330) Checks #42: Commit cb0b0c8 pushed by big-yellow-duck
47s main
main
47s
[gfx1201] Enable RMSNorm support for gfx1201 Checks #41: Pull request #4 synchronize by vllmellm
44s rdna4-rmsnorm-support
rdna4-rmsnorm-support
44s
[gfx1201] Enable quantization kernels for gfx1201 Checks #40: Pull request #3 synchronize by vllmellm
44s rdna4-quant-support
rdna4-quant-support
44s
[gfx1201] Enable RMSNorm support for gfx1201 Checks #39: Pull request #4 synchronize by big-yellow-duck
48s rdna4-rmsnorm-support
rdna4-rmsnorm-support
48s
[gfx1201] Enable quantization kernels for gfx1201 Checks #38: Pull request #3 synchronize by big-yellow-duck
48s rdna4-quant-support
rdna4-quant-support
48s
[gfx1201] Enable RMSNorm support for gfx1201 Checks #37: Pull request #4 opened by big-yellow-duck
46s rdna4-rmsnorm-support
rdna4-rmsnorm-support
46s
[gfx1201] Enable quantization kernels for gfx1201 Checks #36: Pull request #3 opened by big-yellow-duck
46s rdna4-quant-support
rdna4-quant-support
46s
[1] [gfx1201] Add tuned gemm_a8w8_blockscale configs for Qwen3 models for gfx1201 Checks #35: Pull request #2 opened by big-yellow-duck
44s rdna4-ck-gemm_a8w8_blockscale
rdna4-ck-gemm_a8w8_blockscale
44s
[gfx1201] add tuned ck_gemm_a8w8_blockscale configs for various qwen3 models and default case Checks #34: Pull request #1 opened by big-yellow-duck
43s rdna4-quant-support
rdna4-quant-support
43s
opt fuse_qk_norm_rope_blkquant kernel (#2206) Checks #33: Commit cd082f5 pushed by big-yellow-duck
47s main
main
47s
Checks Checks #32: Commit b4370ca pushed by big-yellow-duck
49s main
main
49s
opt fuse_qk_norm_rope_blkquant kernel (#2206) Checks #31: Commit cd082f5 pushed by big-yellow-duck
48s main
main
48s
update dsv3 ptpc a8w8 gemm config (#2253) Checks #30: Commit dc7fefc pushed by big-yellow-duck
48s main
main
48s
Checks Checks #29: Commit 74dcbbc pushed by tjtanaa
43s main
main
43s