Commit Graph

844 Commits

Author SHA1 Message Date
DP Migration
89d522223f under test, not sure no errors 2026-09-01 15:42:42 +00:00
DP Migration
96f4bafcef under test, not sure no errors 2026-09-01 10:28:11 +00:00
DP Migration
94d77cf0b4 under test, not sure no errors 2026-09-01 10:24:14 +00:00
root
8c9d913f3f add pycache clean 2026-09-01 09:11:58 +00:00
root
b168ff9e2d [perf] xllm_fused_qknorm_rope.so compiled+wired, xllm_cache 2026-09-01 06:36:44 +00:00
root
0d88ac4b62 test submit 2026-08-25 16:35:45 +00:00
root
628f8ef603 test submit 2026-08-25 16:23:46 +00:00
root
2ca835fea7 [fix] timeout error 2026-08-25 10:08:10 +00:00
root
f6e2537461 [fix] patch_ops.sh remove envs.py 2026-08-25 06:27:50 +00:00
root
1615a313ea [fix] F.linear→ix_moe_bridge.linear 2026-08-25 04:35:36 +00:00
root
b8f54db5e6 [fix] yaml baseline6 format 2026-08-25 04:33:29 +00:00
root
3308d9bcf4 [fix] baseline7 9x MoE decode speedup 2026-08-25 04:09:43 +00:00
root
1b82bc14a7 [fix] 30s timeout action 2026-08-25 04:05:56 +00:00
root
324fd7f3a9 [fix] docker callback timeout 2026-08-25 03:54:08 +00:00
root
44314afb70 [fix] remove CUDA compilation, use prebuilt .so only (fixes 30min timeout) 2026-08-25 03:29:34 +00:00
root
00654476d3 [fix] baseline7 pyc清除+greedy n>1+fanout宽松+image重试+max_num_seqs env覆盖 2026-08-25 02:36:29 +00:00
root
06d56f6ff8 sub791 docker rizhi log 2026-08-24 17:01:22 +00:00
root
362da0bef9 [fix] t3: cap default_max_tokens to 8192 2026-08-24 09:59:26 +00:00
root
c2edc9a84e [fix] baseline7 delete null line 2026-08-24 07:00:18 +00:00
root
f1fed0d6d5 [fix] baseline7 fix git add qwen3_6_scripts/serving_chat.py! 2026-08-24 06:55:36 +00:00
root
ccf22f25e0 [fix] baseline7 sub791 rizhi 2026-08-24 06:00:13 +00:00
root
367031b3bc [fix] t2_n_2 max_num_seqs; t13 2026-08-24 04:18:10 +00:00
root
3fe0590266 [fix] baseline5 yaml not found template 2026-08-20 14:04:49 +00:00
root
12d2ad55bd [baseline5] fix ctx_len=2147450879 2026-08-20 12:23:50 +00:00
root
56d0c18605 trigger build 2026-08-20 10:50:44 +00:00
root
9050014ec3 trigger rebuild 2026-08-20 10:02:16 +00:00
root
10151b7c91 [fix] baseline5 _forward_prefix_pytorch 0x7FFF7FFF fix 2026-08-20 09:54:28 +00:00
root
fedb48f21e [feat] baseline5 fused linear+allreduce bridge 2026-08-20 08:48:21 +00:00
root
49862ccda4 [fix] baseline5 tribber build 2026-08-20 07:37:26 +00:00
root
684d674fc9 [baseline5] fix template 2026-08-20 06:48:08 +00:00
root
8842a5ffef [fix] baseline5 1.8192->4096 solve oom 2. bridge.linear 导过去 2026-08-20 06:33:38 +00:00
root
882669b0bc delete old md 2026-08-20 02:28:32 +00:00
root
43509e71b1 [fix] baseline5 delay git add qwen3_6_scripts/patch_ops.sh qwen3_6_scripts/patch_chat_template.py computility-run.yaml! errors 2026-08-20 02:26:53 +00:00
root
b7791a0df1 trigger rebuild 2026-08-19 16:31:48 +00:00
root
f7352fa03f [fix] args num 2026-08-19 14:01:25 +00:00
root
9a52068533 [fix] baseline5 fused_add_rms_norm 确实是参数数量不匹配。rms_norm 则是参数数量对了但结果没写回去。两个 bug 叠加导致模型输出全损坏 2026-08-19 09:57:51 +00:00
root
0de522fb4b trigger rebuild 2026-08-19 08:46:08 +00:00
root
552f1448b9 [md] baseline5 worklog 2026-08-19 08:03:09 +00:00
root
79e9208fe4 [fix] baseline5 W2 用 shfl_down 归约 2026-08-19 07:25:33 +00:00
root
989bb943ca trigger rebuild 2026-08-19 06:58:35 +00:00
root
858841a1c4 trigger rebuild 2026-08-19 06:53:18 +00:00
root
7b0eaf144a trigger rebuild 2026-08-19 06:38:07 +00:00
root
243a79b862 [fix] baseline5 volite warp 2026-08-19 06:37:39 +00:00
root
f7e1774cfa trigger rebuild 2026-08-19 05:31:45 +00:00
root
372456bb62 [fix] baseline5 new line delte 2026-08-19 05:31:22 +00:00
root
4d63d394ca [fix] baseline5 fix __shfl_down_sync 2026-08-19 05:30:20 +00:00
root
4ec61094b7 [fix] qkv contiguous 2026-08-19 04:32:42 +00:00
root
647c018dc1 trigger rebuild 2026-08-19 03:39:20 +00:00
root
914dd4a69d ixf copy_blocks 2026-08-19 03:39:03 +00:00
root
bbb347bb0f trigger rebuild 2026-08-19 03:31:13 +00:00