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
root
fccb78df09
Merge branch 'main' of https://dev.modelhub.org.cn/dylanyunlong/project_6 into main
2026-08-18 04:17:58 +00:00
root
8cc6a91b8a
[fix] baseline4 use ix_moe_bridge.so instead of broken ix_full_bridge.so
2026-08-18 04:17:37 +00:00
root
13b12aac4c
[fix] baseline4 rms_norm crash
2026-08-18 03:35:26 +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
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
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
root
8211a45464
platform test baseline4
2026-08-17 07:22:14 +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