dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
752 Commits 1 Branch 0 Tags
bcb18cf3280b7392d126b1bcc696819696c6db6a
Commit Graph

752 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
root
bcb18cf328 trigger rebuild 2026-08-18 03:33:06 +00:00
root
4f9f31f094 [fix] baseline4 debug info 2026-08-18 03:33:06 +00:00
root
448996d386 trigger rebuild 2026-08-18 03:33:06 +00:00
root
716ede67fd trigger rebuild 2026-08-18 03:33:06 +00:00
root
763cda98c5 trigger rebuild 2026-08-18 03:33:06 +00:00
root
2b0d98a867 [fix] baseline4 debug info 2026-08-18 02:53:21 +00:00
root
31aa943248 trigger rebuild 2026-08-18 02:53:21 +00:00
root
902655f1bc trigger rebuild 2026-08-18 02:53:21 +00:00
root
74cdc68a1c trigger rebuild 2026-08-18 02:53:21 +00:00
Claude
6fe1272f13 doc: MoE 5函数符号真相 — 不在预装.so里,由moe_ops_impl.cu自编译 
确认结果:
- topk_softmax, moe_compute_token_index_api, moe_expand_input,
  moe_w16a16_group_gemm, moe_output_reduce_sum
- namespace 是 ixformer::infer (Tensor API), 不是 ixformer::kernels::infer (raw ptr API)
- 4个镜像.so全部nm -D搜过,均无这些符号
- 实现在 ex_engine/csrc/moe_ops_impl.cu (自编译CUDA kernel)
- 由 build_moe_bridge.sh 编译进 ix_full_bridge_v2.so
- kernels.h 里的 ixformer::kernels::infer 是SDK头文件声明(模板+raw ptr)
  我们的 ixformer::infer 是独立实现(torch::Tensor wrapper)
 2026-08-18 02:53:21 +00:00
root
714c41d17b trigger rebuild 2026-08-18 02:32:00 +00:00
root
96ef5f27d3 [fix] baseline4 debug info 2026-08-18 02:20:43 +00:00
Claude
b77743451c debug: rms_norm weight.dim()!=1 — 打印前20次调用的w.shape, x.shape, class 2026-08-18 02:08:37 +00:00
root
e814180e04 trigger rebuild 2026-08-18 01:26:22 +00:00
root
ae27d0405b Merge branch 'main' of https://github.com/dylanyunlon/project_6 2026-08-17 18:11:57 +00:00
Claude
f7b1b2d119 fix: patched_reshape_and_cache signature 7→8 args (k_scale, v_scale) 
Original vllm ops.reshape_and_cache passes 8 args:
  key, value, key_cache, value_cache, slot_mapping, kv_cache_dtype, k_scale, v_scale
Our patch had 7 (single kv_scale) → TypeError on first request → engine dead.
 2026-08-17 18:10:52 +00:00
root
d42b0c1c04 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 2026-08-17 17:45:24 +00:00
Claude
8d969822b4 fix: revert ix_full_bridge.so to d32822c5 original (160KB) 
be5e23f3 rebuilt this .so but introduced ABI mismatch:
  undefined symbol: c10::detail::torchInternalAssertFail
The original 160KB .so does not reference this symbol and works
with the Docker image's libtorch.
 2026-08-17 17:39:21 +00:00
root
f439f67f39 baseline4 trigger rebuild 2026-08-17 17:16:11 +00:00
Claude
f287382f99 fix: update SHA256SUMS for rebuilt ix_full_bridge.so 
ix_full_bridge.so was rebuilt in be5e23f3 (without MoE ixformer::infer deps)
but SHA256SUMS was not updated. install_prebuilt_corex.sh sha256sum --check
fails → set -eo pipefail kills patch_ops.sh → cli_args.py/api_server.py
never deployed → vllm rejects --reasoning-parser qwen3 at startup.
 2026-08-17 17:12:41 +00:00
root
ff18454eeb trigger rebuild 2026-08-17 16:52:37 +00:00
root
be5e23f335 fix: rebuild ix_full_bridge.so without MoE ixformer::infer deps 2026-08-17 16:25:16 +00:00
root
5c97e3dcb8 trigger rebuild 2026-08-17 14:39:56 +00:00
root
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 2026-08-17 14:17:03 +00:00
root
053dc036b8 [fix] prebuilt 的 ix_full_bridge.so 在子进程（没有 GPU 初始化）里被 dlopen 2026-08-17 14:01:36 +00:00
root
9c46f5a04e [fix] baseline4 copy_blocks 崩溃和 ex_engine import 路径两个接线没接对 2026-08-17 13:19:26 +00:00
root
1af45de371 [fix] baseline4 docker build move ex_engine into qwen3_6_scripts, remove COPY ex_engine from Dockerfile 2026-08-17 11:51:01 +00:00
root
c655c1d29e fix: replace symlinks with real files for Docker build 2026-08-17 10:52:34 +00:00
root
657fef6766 trigger rebuild 2026-08-17 10:37:29 +00:00
root
0e21445220 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 into main 2026-08-17 10:11:44 +00:00
root
36909bf964 [fix] prebuilt 2026-08-17 10:11:24 +00:00
root
f10cccf9df [fix] baseline4 :ix_moe_bridge.so 。 v2 bridge 真机编译通过，13函数全导出 2026-08-17 09:18:32 +00:00
Claude
7d6884d15a tool: verify_bridge.sh — 验证prebuilt .so是v1还是v2，缺MoE则自动重编 
5步验证流程:
  Step 1: 定位 prebuilt ix_full_bridge.so
  Step 2: nm -D 检查导出符号 (v1=5函数 vs v2=13函数)
  Step 3: 检查编译源文件+工具链+依赖库
  Step 4: 缺MoE函数则调用 build_moe_bridge.sh 重编
  Step 5: Python import 验证最终 .so 的函数列表
 2026-08-17 08:49:14 +00:00
root
b81a071f84 merge modelhub: bridge_v2 + patch_vllm_ops fix 2026-08-17 08:34:14 +00:00
root
b342eb6b98 [fix] baseline4 fix prebuilt ix_full_bridge.so 大概率是从 v2 编译的 2026-08-17 08:26:54 +00:00
root
c044d04509 merge modelhub: dockerignore fix + build_moe_bridge 2026-08-17 07:54:23 +00:00
root
ba127fe66b delay baseline4 docker build 2026-08-17 07:39:52 +00:00
root
8211a45464 platform test baseline4 2026-08-17 07:22:14 +00:00
root
f7070b2075 platform test baseline4 2026-08-17 07:19:44 +00:00
dev
be4d661191 revert: undo 2 premature pushes (ee516bd2, 9ea0a1d4) — code needs review first 2026-08-17 07:04:50 +00:00
dev
9ea0a1d4f4 fix: resolve all 8 deployment pipeline breaks 
Breaks found and fixed:

1. Dockerfile: COPY 5 individual files → COPY entire ex_engine/
2. patch_ops.sh EX_ENGINE_DIR: /workspace/ex_engine not found → added fallback
3. patch_ops.sh deploy: ix_ops.py to ex_engine/ (flat) → ex_engine/python/ (correct package)
4. ix_startup_patch.py: import from vllm.ex_engine.patch_vllm_ops → vllm.ex_engine.python.patch_vllm_ops
5. ix_moe_bridge.so: only deployed to ex_engine/ → also copy to model_executor/models/ and vllm root
6. ex_engine/__init__.py: missing re-exports → add imports so 'from vllm.ex_engine import x' works
7. gemm_grouped.so: compiled but never imported → add import + flag + prefill GEMM path in qwen3_5.py
8. build_moe_bridge.sh Python heredoc: SCRIPT_DIR not exported + wrong nested path → export + search both layouts

Also added:
- CUTLASS batched GEMM compile step (corex_batched_gemm.so for decode)
- Full ex_engine/python/*.py deployment (was deploying only 2 of 19 files)
- EX_ENGINE_INFRA_AUDIT.md documenting all findings
 2026-08-17 07:01:41 +00:00
dev
ee516bd206 fix: connect ex_engine to Docker build pipeline 
Path breaks fixed:
1. Dockerfile: COPY entire ex_engine/ instead of 5 individual files
2. patch_ops.sh: EX_ENGINE_DIR fallback to /workspace/ex_engine
3. build_moe_bridge.sh: search csrc/ under both SCRIPT_DIR and SCRIPT_DIR/ex_engine

New build steps added to patch_ops.sh:
- Build gemm_grouped.so (CUTLASS Cu10 grouped GEMM, verified on device)
- Build corex_batched_gemm.so (CUTLASS batched GEMM for decode)
- Build ix_moe_bridge.so (7-step fused MoE pipeline)
- Deploy all ex_engine/python/*.py to VLLM_ROOT/ex_engine/python/

Previously broken: ix_ops.py, patch_vllm_ops.py, ix_startup_patch.py
were never deployed because EX_ENGINE_DIR resolved to nonexistent path.
xllm_activation/norm/rope/cache.so were copied but had no Python caller.
 2026-08-17 06:56:11 +00:00
Claude
461addf428 Revert "feat: 10-file algorithm factor system — full 10-layer AST call chain" 
This reverts commit 3581dd5435.
 2026-08-17 05:32:26 +00:00
project6-dev
79562c342d Revert "feat: build_all.sh — compile 3 .so from 10 algorithm factor files" 
This reverts commit 401d33ca6b.
 2026-08-17 05:31:17 +00:00
Claude
3581dd5435 feat: 10-file algorithm factor system — full 10-layer AST call chain 
Layer 1: hw_config.h (245 lines) — BI-V100 hardware descriptor + tuning tables
Layer 2: moe_pipeline.py (461 lines) — MoE 7-step pipeline orchestrator
Layer 3: attn_dispatch.py (270 lines) — Attention prefill/decode dispatch
Layer 4: ilu_ops_api.h (182 lines) — Dispatch signature contract
Layer 5: kernel_moe_ops.cpp (155 lines) — MoE kernel-level ops wrappers
Layer 6: kernel_elem_ops.cpp (210 lines) — Element-wise kernel wrappers
Layer 7: ixformer_infer.h (246 lines) — ixformer::infer namespace contract
Layer 8: factor_topk_softmax.cu (456 lines) — MoE routing CUDA kernel
Layer 9: factor_moe_compute_index.cu (174 lines) — Token index CUDA kernel
Layer 10: factor_moe_combine.cu (154 lines) — Weighted combine CUDA kernel

Total: 2553 lines across 10 files (h/cpp/cu/py)
Upstream reference: 2787 lines across corresponding 10 xllm AST layers

Each file follows the read-read-read-write pattern from upstream xllm,
ds_vllm, and fla repos. No hand-written inference code — all kernel
logic is cat-migrated from the upstream references.
 2026-08-17 05:30:53 +00:00
project6-dev
401d33ca6b feat: build_all.sh — compile 3 .so from 10 algorithm factor files 
AST chain (aligned to xllm ILU layer):
  _ixformer_torch.so (base) → ix_full_bridge.so (7 ops) → Python
  moe_ops_impl.cu (5 CUDA kernels) → ix_moe_bridge.so (7-step MoE) → Python
  gemm_grouped.cu (CUTLASS Cu10) → gemm_grouped.so (verified 1.97x) → Python
  cuinfer_gemm_wrapper.cu → cuinferCustomGemm C API → Python

Symbol sources verified from cat_files/symbol_dumps
 2026-08-17 05:30:21 +00:00
root
512f384a49 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 into main 2026-08-17 04:19:31 +00:00
root
cdcf115037 feat: CUTLASS Cu10 grouped GEMM — real device verified 
BI-V100 real device results:
  moe_group_gemm: err=0.000015 PASS
  moe_decode_cutlass: NaN=False PASS
  cutlass grouped: 4.77ms vs torch.mm loop: 9.38ms → 1.97x speedup

Fix: gemm_grouped.cu ldb=K (not N) for ColumnMajor B view
Link: -lcuinfer from /usr/local/corex-3.2.3/lib64/libcuinfer.so.7
 2026-08-17 04:18:29 +00:00
root
cb926707af Merge branch 'main' of https://github.com/dylanyunlon/project_6 2026-08-17 02:21:09 +00:00
root
beaa8dbb65 Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 2026-08-17 02:18:46 +00:00