Commit Graph

382 Commits

Author SHA1 Message Date
root
0c97b7f520 trigger build 2026-09-02 02:58:01 +00:00
DP Migration
27878c8689 under test, not sure no errors 2026-09-02 01:00:37 +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
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
362da0bef9 [fix] t3: cap default_max_tokens to 8192 2026-08-24 09:59:26 +00:00
root
f1fed0d6d5 [fix] baseline7 fix git add qwen3_6_scripts/serving_chat.py! 2026-08-24 06:55:36 +00:00
root
367031b3bc [fix] t2_n_2 max_num_seqs; t13 2026-08-24 04:18:10 +00:00
root
12d2ad55bd [baseline5] fix ctx_len=2147450879 2026-08-20 12:23:50 +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
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
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
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
79e9208fe4 [fix] baseline5 W2 用 shfl_down 归约 2026-08-19 07:25:33 +00:00
root
243a79b862 [fix] baseline5 volite warp 2026-08-19 06:37:39 +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
914dd4a69d ixf copy_blocks 2026-08-19 03:39:03 +00:00
root
f7ed416754 test line 2026-08-19 03:24:44 +00:00
root
c8e8473367 test docker build 2026-08-19 03:09:44 +00:00
root
7d74ad4e8e [fix] baseline docker build from ex_engine.python.xllm_ops import _get error 2026-08-19 02:46:40 +00:00
root
cbbc3a6100 [fix] \ No newline at end of file 2026-08-19 02:07:29 +00:00
root
679f2c1e29 [fix] baseline4 _xllm_block_copy arg 2026-08-19 01:55:54 +00:00
root
5d2faa3c00 [fix] baseline4 ixf to xllm 2026-08-19 01:07:16 +00:00
root
e1870880c5 [fix ]build baseline4 2026-08-18 17:40:53 +00:00
root
54834c7644 [fix] baseline4 ops_sh fix 2026-08-18 17:26:02 +00:00
root
37a49ee655 [fix] bseline4 sh 添加换行符 2026-08-18 17:05:30 +00:00
root
06f4ce3bb9 [fix] baseline4 ixf_F.copy_blocks名字不匹配 2026-08-18 15:35:03 +00:00
root
8c206feb91 [fix] baseline4 paged_attn.py 的 seq_lens_tensor 包含 0x7FFF7FFF 2026-08-18 10:32:55 +00:00
root
614bad6232 [feat] baseline4 profiling 2026-08-18 10:21:15 +00:00
root
3c53587de2 [fix] baseline4 NaN 0X7FFF7FFF 2026-08-18 09:54:25 +00:00
root
7a02a5bf92 baseline4 NAN 0X7FFF7FFF 2026-08-18 08:37:30 +00:00
root
ab078989da [fix] reshape_paged_cache slot_mapping int64→int32 (C++ data_ptr<int>要求) 2026-08-18 07:41:38 +00:00
root
9e1df1482e [fix] xllm_ops 5处C++参数签名 2026-08-18 07:10:18 +00:00
root
c92135111e [fix] reshape_paged_cache参数顺序 2026-08-18 06:44:01 +00:00
root
b89bd3d72f [fix] ix_moe_bridge pybind名无ix_前缀: ix_paged_attention→paged_attention, ix_linear→linear 2026-08-18 06:14:15 +00:00
root
54a9b572af [fix] xllm_ops 7处函数名匹配.so真实导出符号
- reshape_and_cache → reshape_paged_cache (xllm_cache.so)
- residual_rms_norm → fused_add_rms_norm (xllm_norm.so)
- topk_softmax → moe_fused_topk (xllm_moe.so)
- moe_compute_token_index → moe_compute_index (xllm_moe.so)
- ix_full_bridge → ix_moe_bridge (paged_attention, ix_linear)
- ix_linear 5参数 → 3参数 (input, weight, bias)
- check_all: ix_moe_bridge改为required, ix_full_bridge改为optional
2026-08-18 06:11:03 +00:00