apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 08:21:53 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[XPU] Unify Spec and non-spec branch.(#6947) (#7180)

Browse Source 
* [XPU] cherry-pick PR-6947

* [XPU] use unified_update_model_status.

* refactor xpu_model_runner.

* refactor sampler.

* fix codestyle.

* Fix XPU speculative decoding: rename output tensors to cu_seqlens_q_output/batch_id_per_token_output, correct
  WRAPPER_CHECK_PTR types, and fix dynamic gather shape in verify_draft_tokens path.

* fix codestyle.

* replace output_padding_offset with is_speculative flag in gather_next_token.

* rename hiddden_states.

* unify cu_seqlens_q_output and batch_id_per_token_output init.

---------

Co-authored-by: cmcamdy <1027740945@qq.com>
This commit is contained in:
Jiajun Ji
2026-04-16 14:58:38 +08:00
committed by GitHub
parent 17002edc47
commit 29495b2cf1
9 changed files with 226 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/xpu_ops/src/plugin/include/xpu/plugin.h
-1
View File
@@ -766,7 +766,6 @@ DLL_EXPORT int speculate_limit_thinking_content_length_kernel(
const int eos_token_id_len,
const int inject_len,
const bool splitwise_role_is_decode);
DLL_EXPORT int verify_draft_tokens(
api::Context* ctx,
// Core I/O