All Workflows Performance Benchmarks CI Documentation GPU Tests Release

801 workflow runs

Actor

All actors osobh

Status

All status Success Failure Canceled Skipped Waiting Running Blocked Canceling

Branch

All branches main

feat(batch7): interleaved 1F1B, attention-selective checkpointing, flash decoding

GPU Tests #111:Commit b45a58792d pushed by osobh

main

2026-06-27 15:13:15 +00:00

11h6m8s

View workflow file

feat(batch7): interleaved 1F1B, attention-selective checkpointing, flash decoding

Documentation #110:Commit b45a58792d pushed by osobh

main

2026-06-27 04:07:20 +00:00

15s

View workflow file

feat(batch7): interleaved 1F1B, attention-selective checkpointing, flash decoding

CI #109:Commit b45a58792d pushed by osobh

main

2026-06-27 06:48:43 +00:00

2h41m38s

View workflow file

feat(batch7): interleaved 1F1B, attention-selective checkpointing, flash decoding

Performance Benchmarks #108:Commit b45a58792d pushed by osobh

main

2026-06-27 04:07:10 +00:00

11s

View workflow file

feat(batch6): windowed acceptance metrics, KV INT8 quant, col/row-parallel linear

GPU Tests #107:Commit 0e1d6a74b6 pushed by osobh

main

2026-06-27 15:13:15 +00:00

11h18m52s

View workflow file

feat(batch6): windowed acceptance metrics, KV INT8 quant, col/row-parallel linear

Documentation #106:Commit 0e1d6a74b6 pushed by osobh

main

2026-06-27 03:54:37 +00:00

20s

View workflow file

feat(batch6): windowed acceptance metrics, KV INT8 quant, col/row-parallel linear

CI #105:Commit 0e1d6a74b6 pushed by osobh

main

2026-06-27 06:48:14 +00:00

2h53m53s

View workflow file

feat(batch6): windowed acceptance metrics, KV INT8 quant, col/row-parallel linear

Performance Benchmarks #104:Commit 0e1d6a74b6 pushed by osobh

main

2026-06-27 04:02:12 +00:00

7m58s

View workflow file

feat(batch5): mid-batch injection, PagedAttn v2 defrag, fused RoPE kernel

Documentation #103:Commit ef786c0ab1 pushed by osobh

main

2026-06-27 01:41:05 +00:00

10s

View workflow file

feat(batch5): mid-batch injection, PagedAttn v2 defrag, fused RoPE kernel

CI #102:Commit ef786c0ab1 pushed by osobh

main

2026-06-27 06:47:06 +00:00

5h6m11s

View workflow file

feat(batch5): mid-batch injection, PagedAttn v2 defrag, fused RoPE kernel

Performance Benchmarks #101:Commit ef786c0ab1 pushed by osobh

main

2026-06-27 01:42:22 +00:00

1m28s

View workflow file

feat(perf): GPU perf batch 4 — SmoothQuant INT8 forward, varlen FA, inference graph capture

GPU Tests #100:Commit d6769ef641 pushed by osobh

main

2026-06-27 15:13:15 +00:00

14h1m57s

View workflow file

feat(perf): GPU perf batch 4 — SmoothQuant INT8 forward, varlen FA, inference graph capture

Documentation #99:Commit d6769ef641 pushed by osobh

main

2026-06-27 01:11:28 +00:00

10s

View workflow file

feat(perf): GPU perf batch 4 — SmoothQuant INT8 forward, varlen FA, inference graph capture

CI #98:Commit d6769ef641 pushed by osobh

main

2026-06-27 06:46:38 +00:00

5h35m17s

View workflow file

feat(perf): GPU perf batch 4 — SmoothQuant INT8 forward, varlen FA, inference graph capture

Performance Benchmarks #97:Commit d6769ef641 pushed by osobh

main

2026-06-27 01:12:26 +00:00

1m10s

View workflow file

feat(perf): GPU perf batch 3 — W4A16 AWQ matmul, FSDP2 hooks, RMSNorm+SwiGLU fused kernel

Documentation #96:Commit 311eb23dbd pushed by osobh

main

2026-06-27 00:37:02 +00:00

9s

View workflow file

feat(perf): GPU perf batch 3 — W4A16 AWQ matmul, FSDP2 hooks, RMSNorm+SwiGLU fused kernel

CI #95:Commit 311eb23dbd pushed by osobh

main

2026-06-27 06:46:37 +00:00

6h9m44s

View workflow file

feat(perf): GPU perf batch 3 — W4A16 AWQ matmul, FSDP2 hooks, RMSNorm+SwiGLU fused kernel

Performance Benchmarks #94:Commit 311eb23dbd pushed by osobh

main

2026-06-27 00:38:41 +00:00

1m51s

View workflow file

feat(perf): GPU perf batch 2 — EAGLE-3 dynamic draft trees + GaLore-2 optimizer

GPU Tests #93:Commit a670045f46 pushed by osobh

main

2026-06-27 15:13:14 +00:00

14h36m28s

View workflow file

feat(perf): GPU perf batch 2 — EAGLE-3 dynamic draft trees + GaLore-2 optimizer

Documentation #92:Commit a670045f46 pushed by osobh

main

2026-06-27 00:36:49 +00:00

11s

View workflow file

feat(perf): GPU perf batch 2 — EAGLE-3 dynamic draft trees + GaLore-2 optimizer

CI #91:Commit a670045f46 pushed by osobh

main

2026-06-27 06:45:49 +00:00

6h9m7s

View workflow file

feat(perf): GPU perf batch 2 — EAGLE-3 dynamic draft trees + GaLore-2 optimizer

Performance Benchmarks #90:Commit a670045f46 pushed by osobh

main

2026-06-27 00:36:47 +00:00

10s

View workflow file

feat(perf): GPU perf batch 1 — wire GPU execution paths for FP8, FA3, CUDA Graphs, SnapKV

GPU Tests #89:Commit 082a50e3a0 pushed by osobh

main

2026-06-27 15:13:14 +00:00

14h36m37s

View workflow file

feat(perf): GPU perf batch 1 — wire GPU execution paths for FP8, FA3, CUDA Graphs, SnapKV

Documentation #88:Commit 082a50e3a0 pushed by osobh

main

2026-06-27 00:36:39 +00:00

9s

View workflow file

feat(perf): GPU perf batch 1 — wire GPU execution paths for FP8, FA3, CUDA Graphs, SnapKV

CI #87:Commit 082a50e3a0 pushed by osobh

main

2026-06-27 06:44:47 +00:00

6h8m13s

View workflow file

feat(perf): GPU perf batch 1 — wire GPU execution paths for FP8, FA3, CUDA Graphs, SnapKV

Performance Benchmarks #86:Commit 082a50e3a0 pushed by osobh

main

2026-06-27 00:36:36 +00:00

8s

View workflow file

feat(perf): GPU perf batch 1 — FP8, FA3 Blackwell, CUDA Graphs, SnapKV, prefix cache

GPU Tests #85:Commit 1eb89c5b2b pushed by osobh

main

2026-06-27 15:13:13 +00:00

14h36m47s

View workflow file

feat(perf): GPU perf batch 1 — FP8, FA3 Blackwell, CUDA Graphs, SnapKV, prefix cache

Documentation #84:Commit 1eb89c5b2b pushed by osobh

main

2026-06-27 00:36:30 +00:00

16s

View workflow file

feat(perf): GPU perf batch 1 — FP8, FA3 Blackwell, CUDA Graphs, SnapKV, prefix cache

CI #83:Commit 1eb89c5b2b pushed by osobh

main

2026-06-27 06:45:49 +00:00

6h9m31s

View workflow file

feat(perf): GPU perf batch 1 — FP8, FA3 Blackwell, CUDA Graphs, SnapKV, prefix cache

Performance Benchmarks #82:Commit 1eb89c5b2b pushed by osobh

main

2026-06-27 00:36:28 +00:00

15s

View workflow file