Commit Graph

  • 614bad6232 [feat] baseline4 profiling root 2026-08-18 10:21:15 +00:00
  • 3c53587de2 [fix] baseline4 NaN 0X7FFF7FFF root 2026-08-18 09:54:25 +00:00
  • 7a02a5bf92 baseline4 NAN 0X7FFF7FFF root 2026-08-18 08:37:30 +00:00
  • ab078989da [fix] reshape_paged_cache slot_mapping int64→int32 (C++ data_ptr<int>要求) root 2026-08-18 07:41:38 +00:00
  • ac6d51c936 delete prd.md root 2026-08-18 07:19:16 +00:00
  • 47f6d30c2d trigger rebuild root 2026-08-18 07:12:13 +00:00
  • 56694e5075 trigger rebuild root 2026-08-18 07:12:01 +00:00
  • 9e1df1482e [fix] xllm_ops 5处C++参数签名 root 2026-08-18 07:10:18 +00:00
  • c92135111e [fix] reshape_paged_cache参数顺序 root 2026-08-18 06:44:01 +00:00
  • 62e3312258 trigger rebuild root 2026-08-18 06:15:05 +00:00
  • b89bd3d72f [fix] ix_moe_bridge pybind名无ix_前缀: ix_paged_attention→paged_attention, ix_linear→linear root 2026-08-18 06:14:15 +00:00
  • 54a9b572af [fix] xllm_ops 7处函数名匹配.so真实导出符号 root 2026-08-18 06:11:03 +00:00
  • fccb78df09 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 into main root 2026-08-18 04:17:58 +00:00
  • 8cc6a91b8a [fix] baseline4 use ix_moe_bridge.so instead of broken ix_full_bridge.so root 2026-08-18 04:17:37 +00:00
  • 13b12aac4c [fix] baseline4 rms_norm crash root 2026-08-18 03:35:26 +00:00
  • d6d12c56d8 [fix] baseline4 debug info root 2026-08-18 02:20:43 +00:00
  • c6eb038429 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 63e574ad0b trigger rebuild root 2026-08-18 01:26:22 +00:00
  • da1382bb23 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • bcb18cf328 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 4f9f31f094 [fix] baseline4 debug info root 2026-08-18 02:20:43 +00:00
  • 448996d386 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 716ede67fd trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 763cda98c5 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 2b0d98a867 [fix] baseline4 debug info root 2026-08-18 02:20:43 +00:00
  • 31aa943248 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 902655f1bc trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 74cdc68a1c trigger rebuild root 2026-08-18 01:26:22 +00:00
  • 6fe1272f13 doc: MoE 5函数符号真相 — 不在预装.so里,由moe_ops_impl.cu自编译 Claude 2026-08-18 02:19:23 +00:00
  • 714c41d17b trigger rebuild root 2026-08-18 02:32:00 +00:00
  • 96ef5f27d3 [fix] baseline4 debug info root 2026-08-18 02:20:43 +00:00
  • b77743451c debug: rms_norm weight.dim()!=1 — 打印前20次调用的w.shape, x.shape, class Claude 2026-08-18 01:58:15 +00:00
  • e814180e04 trigger rebuild root 2026-08-18 01:26:22 +00:00
  • ae27d0405b Merge branch 'main' of https://github.com/dylanyunlon/project_6 root 2026-08-17 18:11:57 +00:00
  • f7b1b2d119 fix: patched_reshape_and_cache signature 7→8 args (k_scale, v_scale) Claude 2026-08-17 18:10:52 +00:00
  • d42b0c1c04 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 root 2026-08-17 17:45:24 +00:00
  • 8d969822b4 fix: revert ix_full_bridge.so to d32822c5 original (160KB) Claude 2026-08-17 17:39:21 +00:00
  • f439f67f39 baseline4 trigger rebuild root 2026-08-17 17:16:11 +00:00
  • f287382f99 fix: update SHA256SUMS for rebuilt ix_full_bridge.so Claude 2026-08-17 17:12:41 +00:00
  • ff18454eeb trigger rebuild root 2026-08-17 16:52:37 +00:00
  • be5e23f335 fix: rebuild ix_full_bridge.so without MoE ixformer::infer deps root 2026-08-17 16:25:16 +00:00
  • 5c97e3dcb8 trigger rebuild root 2026-08-17 14:39:56 +00:00
  • 5b96a91156 [fix] baseline4 不是 CUDA 不可用,是 .so 在非主进程里被 dlopen 时段错误。需要用进程级别的判断 root 2026-08-17 14:17:03 +00:00
  • 053dc036b8 [fix] prebuilt 的 ix_full_bridge.so 在子进程(没有 GPU 初始化)里被 dlopen root 2026-08-17 14:01:36 +00:00
  • 9c46f5a04e [fix] baseline4 copy_blocks 崩溃和 ex_engine import 路径两个接线没接对 root 2026-08-17 13:19:26 +00:00
  • 1af45de371 [fix] baseline4 docker build move ex_engine into qwen3_6_scripts, remove COPY ex_engine from Dockerfile root 2026-08-17 11:51:01 +00:00
  • c655c1d29e fix: replace symlinks with real files for Docker build root 2026-08-17 10:52:34 +00:00
  • 657fef6766 trigger rebuild root 2026-08-17 10:37:29 +00:00
  • 0e21445220 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 into main root 2026-08-17 10:11:44 +00:00
  • 36909bf964 [fix] prebuilt root 2026-08-17 10:11:24 +00:00
  • f10cccf9df [fix] baseline4 :ix_moe_bridge.so 。 v2 bridge 真机编译通过,13函数全导出 root 2026-08-17 09:18:32 +00:00
  • 7d6884d15a tool: verify_bridge.sh — 验证prebuilt .so是v1还是v2,缺MoE则自动重编 Claude 2026-08-17 08:49:14 +00:00
  • b81a071f84 merge modelhub: bridge_v2 + patch_vllm_ops fix root 2026-08-17 08:34:14 +00:00
  • b342eb6b98 [fix] baseline4 fix prebuilt ix_full_bridge.so 大概率是从 v2 编译的 root 2026-08-17 08:26:54 +00:00
  • c044d04509 merge modelhub: dockerignore fix + build_moe_bridge root 2026-08-17 07:54:23 +00:00
  • ba127fe66b delay baseline4 docker build root 2026-08-17 07:39:52 +00:00
  • 8211a45464 platform test baseline4 root 2026-08-17 07:19:44 +00:00
  • f7070b2075 platform test baseline4 root 2026-08-17 07:19:44 +00:00
  • be4d661191 revert: undo 2 premature pushes (ee516bd2, 9ea0a1d4) — code needs review first dev 2026-08-17 07:04:50 +00:00
  • 9ea0a1d4f4 fix: resolve all 8 deployment pipeline breaks dev 2026-08-17 07:01:41 +00:00
  • ee516bd206 fix: connect ex_engine to Docker build pipeline dev 2026-08-17 06:56:11 +00:00
  • 461addf428 Revert "feat: 10-file algorithm factor system — full 10-layer AST call chain" Claude 2026-08-17 05:32:19 +00:00
  • 79562c342d Revert "feat: build_all.sh — compile 3 .so from 10 algorithm factor files" project6-dev 2026-08-17 05:31:05 +00:00
  • 3581dd5435 feat: 10-file algorithm factor system — full 10-layer AST call chain Claude 2026-08-17 05:30:22 +00:00
  • 401d33ca6b feat: build_all.sh — compile 3 .so from 10 algorithm factor files project6-dev 2026-08-17 05:30:21 +00:00
  • 512f384a49 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 into main root 2026-08-17 04:19:31 +00:00
  • cdcf115037 feat: CUTLASS Cu10 grouped GEMM — real device verified root 2026-08-17 04:18:29 +00:00
  • cb926707af Merge branch 'main' of https://github.com/dylanyunlon/project_6 root 2026-08-17 02:21:09 +00:00
  • beaa8dbb65 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 root 2026-08-17 02:18:46 +00:00
  • 03be5f2b15 [feat] group gemm root 2026-08-17 02:16:58 +00:00
  • 330669b309 Revert "fix: ix_full_bridge_v2.cpp — align namespace+signatures to real nm -D symbol dump" Claude 2026-08-17 02:08:03 +00:00
  • 5c03156978 fix: ix_full_bridge_v2.cpp — align namespace+signatures to real nm -D symbol dump Claude 2026-08-17 02:04:47 +00:00
  • 34a8fbf27e revert: undo 2 premature pushes (c54923a1, 49034d1d) — code needs review first project_6 2026-08-16 17:48:17 +00:00
  • 49034d1d09 feat: 10-file MoE bridge pipeline — compile, dispatch, patch, test project_6 2026-08-16 17:46:53 +00:00
  • c54923a17e feat: implement 5 missing MoE ops — topk_softmax + token_index + expand + group_gemm + combine project_6 2026-08-16 17:35:08 +00:00
  • 3712c06861 data: full symbol dumps root 2026-08-16 17:15:11 +00:00
  • dec268d252 data: full symbol dumps root 2026-08-16 17:15:11 +00:00
  • 415ca12afc fix: group_gemm format "TN" + Layer 3 ops_api dispatch from xllm upstream project_6 2026-08-16 16:09:15 +00:00
  • 5172f94b1f Revert "feat: 3-tier ixformer flash prefill dispatch + OpenCompass max_tokens clamp + n>1 fanout + index sanitizer" Claude 2026-08-16 15:42:36 +00:00
  • 7a7ddf38db Revert "test: deploy_and_verify.sh — pull+patch+probe ixformer backends+clamp test" Claude 2026-08-16 15:42:36 +00:00
  • 587e18309b test: deploy_and_verify.sh — pull+patch+probe ixformer backends+clamp test Claude 2026-08-16 15:40:47 +00:00
  • cdec569977 feat: 3-tier ixformer flash prefill dispatch + OpenCompass max_tokens clamp + n>1 fanout + index sanitizer Claude 2026-08-16 15:37:23 +00:00
  • 522e8376b6 data: sub 694 (683分) 日志 + resolve merge root 2026-08-16 15:28:08 +00:00
  • 4189f44d27 test: dump ALL symbols from ALL ixformer/cuinfer .so — no grep filter, find what we missed Claude 2026-08-16 04:58:39 +00:00
  • 8eabbac857 test: probe_model_shapes.sh — 真机验证模型config和MoE权重shape Claude 2026-08-15 15:05:26 +00:00
  • b7149f810a fix: decode MoE路径对齐base — F.linear+bmm替换pre-transpose+bmm Claude 2026-08-15 14:55:01 +00:00
  • ea2c15f699 fix: decode MoE路径对齐base — F.linear+bmm替换pre-transpose+bmm Claude 2026-08-15 14:55:01 +00:00
  • b187f52ced data: so import chain probe root 2026-08-15 14:53:57 +00:00
  • ee62ea13ba data: so import chain probe root 2026-08-15 14:49:42 +00:00
  • 924e48b502 data: so import chain probe root 2026-08-15 14:49:42 +00:00
  • 1700c35bd7 test: probe_so_import_chain.sh — 验证.so部署路径+import链+flag值+shape匹配 Claude 2026-08-15 14:46:49 +00:00
  • c290278b35 test: probe_so_import_chain.sh — 验证.so部署路径+import链+flag值+shape匹配 Claude 2026-08-15 14:46:49 +00:00
  • a6cc233880 data: base MoE forward + corex_moe签名 root 2026-08-15 14:39:03 +00:00
  • 784dea96c0 data: base MoE forward + corex_moe签名 root 2026-08-15 14:39:03 +00:00
  • adf05b6bfb test: probe_base_moe_forward.sh — cat base qwen3_5.py的完整MoE forward + 所有corex_moe_*.so签名 Claude 2026-08-15 14:36:29 +00:00
  • 7a8545f7c2 test: push_probe_results.sh — 真机commit probe结果到modelhub Claude 2026-08-15 14:34:49 +00:00
  • b00429d81c test: probe_base_moe_forward.sh — cat base qwen3_5.py的完整MoE forward + 所有corex_moe_*.so签名 Claude 2026-08-15 14:36:29 +00:00
  • 6a4459d405 data: probe bridge output root 2026-08-15 14:35:07 +00:00
  • 437ad8aaa4 data: probe bridge output root 2026-08-15 14:35:07 +00:00
  • 6e22415a91 test: push_probe_results.sh — 真机commit probe结果到modelhub Claude 2026-08-15 14:34:49 +00:00