Commit Graph
20 Commits
Author SHA1 Message Date
tzhouamandClaude Opus 5 9a399adba8 chore: satisfy changed-file policy
Scoped pre-commit over the 27 files this rebase touches: ruff format
reflow, the vLLM-Omni SPDX copyright line on the new modules, and wording
the typos hook rejected.

The Python 3.10 mypy hook still reports 24 errors across five of these
files. All 24 sit on pre-existing lines; none fall on a line this rebase
changed, which the repository documents as the CI-skipped condition.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0146Xu5Sgj4vXxLxvLjV5YPj
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:53 +08:00
tzhouamandClaude Opus 5 08884c4cfb rebase: adapt to vLLM 0.29 callback, embedding and video decoder changes
Four unrelated 0.29 surface changes, each reproduced locally against the
pinned f5c3cc24 build:

- PromptUpdateDetails.is_embed now takes only the full token list. The
  Bagel img2img replacement still declared (tok, seq), which crashed
  stage-0 engine core startup and produced the Distributed and Qwen3-Omni
  "no live replica" failures rather than anything KV related.

- dispatch_unquantized_gemm gained a linear_backend argument and is called
  with it. The CPU-forcing test stubs took no arguments; they now accept
  and ignore whatever upstream passes so a further signature change does
  not break them again.

- VocabParallelEmbedding gained a fused kernel that engages whenever
  tp_size > 1 on CUDA, and it has no CPU implementation. The encoder TP
  fixtures drive CPU tensors under a faked TP group, so they pin the
  portable masked path.

- The pyav video decoder backend was removed; valid options are now
  opencv, torchcodec, pynvvideocodec and deepstream. The OpenAI video
  endpoint hardcoded pyav, which turned every video request into a 400.
  It moves to opencv, the upstream default.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0146Xu5Sgj4vXxLxvLjV5YPj
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:53 +08:00
tzhouam f9879239ba chore: satisfy changed-file policy
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:52 +08:00
tzhouam 87a1fd8da2 rebase: adapt to vLLM v0.29 APIs
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:52 +08:00
Joshna-MedisettyandCursor 24c49cf392 [Bugfix][XPU] Add MoTRMSNorm.forward_xpu delegating to forward_native (#5568)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Signed-off-by: Joshna-Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-02 23:06:17 -05:00
Wenjia LiandWeiQing Chen d9980c75e8 Perf/minimax h3 dit swiglu rope cache npu (#6410)
Signed-off-by: Wenjia Li <wjialish@gmail.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-29 09:14:52 +00:00
XiongZhongwei 40dcfdbb43 [Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040)
Signed-off-by: MarkPoloChina <1228479724@qq.com>
Signed-off-by: XiongZhongwei <1228479724@qq.com>
2026-08-26 09:14:05 +08:00
596c16a550 [Kernel] Fuse Q/K RMSNorm and RoPE (#5990)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: Mengjie Zhao <zmj0129@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-14 00:46:59 +00:00
Zhou TaichangandClaude Opus 5 2ce15ab7a0 [Rebase] Rebase to vllm 0.27.0 (#5976)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 15:23:46 +00:00
Weiming LiaoandHongsheng Liu 592637015f [BugFix][NPU] MiniMax-H3 RoPE crash: add the missing batch dim before the mindiesd kernel (#5896)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-09 14:08:43 +00:00
fan2956andFan f2e3d2e25b [Perf] Minimax-H3 support fused RMSNorm and RoPE opt (#5801)
Signed-off-by: Fan <fan@FandeMacBook-Air.local>
Co-authored-by: Fan <fan@FandeMacBook-Air.local>
2026-08-06 11:39:27 +08:00
wangyu 7c17111ff5 [Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951)
Signed-off-by: wangyu <410167048@qq.com>
2026-07-29 23:53:03 +08:00
e108cbb510 [NPU][HunyuanImage3] Adapt diffusion FusedMoE for vLLM >= 0.24.0 (#5167)
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-27 22:41:34 +08:00
Ting FU 815abce2ba [BugFix] fix possible shape mismatch when using ROPE (#4655)
Signed-off-by: Semmer <semmer@live.cn>
2026-07-07 17:54:39 +08:00
Zhou Taichang 7b837944a1 [Rebase] Rebase to vllm 0.23.0 (#4286)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-06-13 16:43:02 +00:00
Junhong Liu 6be59f7d19 [Fix] Fix RMSNorm inductor KeyError under HSDP + torch.compile (#3460)
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
2026-05-11 22:56:54 +08:00
Lancer bb69cbc9f1 [Perf] Optimize RMSNorm in Z-Image (#3304)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
2026-05-04 17:34:43 +08:00
Will.houandwillamhou 15684518d0 perf(helios): replace strided RoPE with stack+flatten for contiguous memory (#2474)
Signed-off-by: willamhou <willamhou@ceresman.com>
Co-authored-by: willamhou <willamhou@ceresman.com>
2026-04-19 20:28:48 +08:00
fan2956andgcanlin f1cb4ebe4c [PERF] Wan2.2 support rmsnorm fused op (#2583)
Signed-off-by: fan2956 <zhoufan53@huawei.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
2026-04-16 03:21:34 -07:00
Yi LiuandHongsheng Liu c1d2dcc3ac [AutoRound] Add offline quantized W4A16 model support (#1777)
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-04-02 13:57:53 +08:00