Skip to content

Actions: EmbeddedLLM/aiter

Actions

vLLM Benchmark

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
vllm_benchmark.yaml
32 workflow runs
32 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Merge branch 'ROCm:main' into main vLLM Benchmark #32: Commit 74dcbbc pushed by tjtanaa
1d 0h 1m 10s main
main
1d 0h 1m 10s
Merge branch 'ROCm:main' into main vLLM Benchmark #31: Commit b94e207 pushed by iAmir97
1d 0h 1m 12s main
main
1d 0h 1m 12s
Merge branch 'ROCm:main' into main vLLM Benchmark #30: Commit 3f8fe9b pushed by tjtanaa
1d 0h 1m 15s main
main
1d 0h 1m 15s
Merge branch 'ROCm:main' into main vLLM Benchmark #29: Commit 5f0e3b4 pushed by iAmir97
1d 0h 1m 11s main
main
1d 0h 1m 11s
Merge branch 'ROCm:main' into main vLLM Benchmark #28: Commit b645bcb pushed by tjtanaa
1d 0h 1m 11s main
main
1d 0h 1m 11s
Merge branch 'ROCm:main' into main vLLM Benchmark #27: Commit 1a286e8 pushed by tjtanaa
1d 0h 0m 42s main
main
1d 0h 0m 42s
Merge branch 'ROCm:main' into main vLLM Benchmark #26: Commit e532f3a pushed by vllmellm
1d 5h 41m 41s main
main
1d 5h 41m 41s
added tuned gemms for r9700 vLLM Benchmark #25: Commit e0c5114 pushed by big-yellow-duck
1d 0h 1m 9s main
main
1d 0h 1m 9s
feat: Adaptive topk algorithm selection based on input characteristic… vLLM Benchmark #24: Commit f174268 pushed by iAmir97
1d 9h 31m 52s main
main
1d 9h 31m 52s
fix tuner (#1701) vLLM Benchmark #23: Commit a9d356f pushed by vllmellm
1d 0h 1m 11s main
main
1d 0h 1m 11s
mha api refactor (#1573) vLLM Benchmark #22: Commit d0c313d pushed by vllmellm
1d 0h 1m 11s main
main
1d 0h 1m 11s
[MHA V3] Remove uses of AITER_ASM_DIR and embed code objects (#1597) vLLM Benchmark #21: Commit ba9047e pushed by vllmellm
1d 4h 24m 1s main
main
1d 4h 24m 1s
Add paged attention decode with Gluon JIT/AOT for AMD CDNA3 (#1383) vLLM Benchmark #20: Commit 5997daf pushed by vllmellm
19h 2m 57s main
main
19h 2m 57s
Initial development of triton based communication primitives using Ir… vLLM Benchmark #19: Commit 62ea289 pushed by vllmellm
1d 5h 46m 30s main
main
1d 5h 46m 30s
Add fused bias support for GMM and bias‑gradient/accumulate support f… vLLM Benchmark #18: Commit 04dc719 pushed by vllmellm
1d 0h 1m 15s main
main
1d 0h 1m 15s
Fused qk rope cat and cache mla (#1380) vLLM Benchmark #17: Commit 23ff415 pushed by vllmellm
1d 0h 30m 28s main
main
1d 0h 30m 28s
speedup large m small n rmsnorm triton kernel case (#1350) vLLM Benchmark #16: Commit 8c3b26d pushed by vllmellm
21h 11m 23s main
main
21h 11m 23s
prebuild1/2/3 pass (#1574) vLLM Benchmark #15: Commit 2212234 pushed by vllmellm
1d 9h 21m 34s main
main
1d 9h 21m 34s
fix torch 2.9 deepseek-0528 error (#1577) vLLM Benchmark #14: Commit 56c1891 pushed by vllmellm
1d 0h 1m 10s main
main
1d 0h 1m 10s
fix bf16 gemm tune with bias True (#1520) vLLM Benchmark #13: Commit 78ef273 pushed by vllmellm
1d 16h 50m 53s main
main
1d 16h 50m 53s
[TRITON] Add MoE GEMM a8w8 kernel (#1356) vLLM Benchmark #12: Commit f248d46 pushed by vllmellm
1d 0h 1m 11s main
main
1d 0h 1m 11s
[fix]: fused_ar_rms interface (#1518) vLLM Benchmark #11: Commit 880ac0e pushed by vllmellm
1d 0h 0m 41s main
main
1d 0h 0m 41s
Support mori in aiter (#1453) vLLM Benchmark #10: Commit 603e527 pushed by vllmellm
1d 0h 1m 13s main
main
1d 0h 1m 13s
[PA](fix): fix format error in str (#1486) vLLM Benchmark #9: Commit 68f5a6b pushed by vllmellm
1d 0h 1m 11s main
main
1d 0h 1m 11s
fix: Triton MXFP4 mantissa rounding (#975) vLLM Benchmark #8: Commit f4e4188 pushed by iAmir97
1d 0h 1m 11s main
main
1d 0h 1m 11s