33e01f22a8
[Feature][Sampling] Extend top-k_top-p sampling to all backends and unify greedy decoding with top_k=1 ( #6894 )
...
* update sampling
* fix
* fix
* fix mtp
* fix test
2026-03-19 01:43:10 -07:00
fb6c56dfd5
[BugFix][DataProcessor] Force top_k=1 for greedy decoding when temperature=0 ( #6748 )
...
* [BugFix] Force top_k=1 for greedy decoding when temperature=0
When temperature is set to 0 (greedy decoding), only setting temperature
to a small epsilon is insufficient — the sampling kernel may still pick
non-top-1 tokens. Explicitly set top_k=1 in all processors to guarantee
argmax behavior.
Additionally, add argmax fast-path in top_k_top_p_sampling() under
FD_DETERMINISTIC_MODE to handle non-rejection sampling backends that
ignore top_k parameter.
* Extract greedy decoding from FD_DETERMINISTIC_MODE guard
top_k=1 → argmax is a correctness optimization, not deterministic-specific.
Remove the FD_DETERMINISTIC_MODE guard so all-greedy fast-path and
mixed-batch override work unconditionally.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* Update test_torch_model.py
---------
Co-authored-by: gongweibao <gognweibao@baidu.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2026-03-18 17:36:43 +08:00
28f7727a3d
[Feature] Set overlap schedule as default ( #6668 )
...
* overlap default
2026-03-09 22:34:54 +08:00
30f9f33f34
[Feature][BugFix][OP] Enhance Deterministic Inference Mode with Kernel-level Fixes and Batch-invariant BMM ( #6610 )
...
* add fa deter
* add ut
* add long sentence
* fix basic
* fix bugs
* fix adn
* fix first
* fix single
* fix single
* fix single test
* refine
* add more test
* refine comments
* add comments of bmm
* fix ci
* remove probe
* add
* remove not need
* refine tests
* fix comments and refine code
* refine code
* refine test
* refine test
* mv 4cards tests
* fix tests
* add
* fix comments
* fix cover
* fix cover
---------
Co-authored-by: gongweibao <gognweibao@baidu.com >
2026-03-09 10:27:53 +08:00
97eee75677
[Feature] GPU Memory Optimization and Retirement of V0 Scheduler ( #6407 )
...
* Optim GPU Mem Usage
---------
Co-authored-by: huzesen <huzesen@baidu.com >
2026-02-28 15:07:43 +08:00
60e75ea8e8
[Iluvatar][CI] Fix cannot import get_stop ( #6165 )
2026-02-10 16:57:23 +08:00
2b4748de4f
[MTP] refactor MTP pre_process ( #6358 )
2026-02-09 10:47:15 +08:00
030647521a
[Metax] adapt to the latest develop ( #6282 )
2026-01-29 23:21:20 -08:00
c4abb01f9c
[Metax][Fix] fix 'get_token_penalty_multi_scores' input error based (PaddlePaddle#6069) ( #6266 )
2026-01-29 19:24:36 +08:00
7d6c87c29e
[Others] Support constrained decoding when enable_thinking is false ( #6248 )
...
* support constrained decoding when enable_thinking is false
* fix
* fix
* fix
2026-01-28 00:05:17 -08:00
ce06c6dfb3
[BugFix] Fix token_penalty kernel ( #6069 )
...
* fix token_penalty kernel
* try to fix xpu
* fix xpu
* fix unit test
2026-01-28 12:03:05 +08:00
49617d9832
[Feature]Support tag phase token enforce generation ( #6034 )
...
* support tag phase token enforce generation
* optimize note and some feature
* fix sampler unit test
---------
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2026-01-15 03:59:55 -08:00
9f4977eb74
[xpu] support mtp for xpu(mix) ( #5274 )
...
* [XPU] support kernel for mtp(base)
* [XPU] support kernel for mtp(base)
* format
* format
* format
* fix gather next token
* fix step && add test
* fix
* mv pre/post process
* add adjust batch / gather next token for mtp
* fix code style
* fix mtp kenrel name
* fix mtp kernel test
* mv xpu pre/post process
* mv xpu pre/post process
* [xpu] support mtp
* fix code style
2025-12-01 11:03:14 +08:00
47595a2480
[Feature] support mtp logprob ( #4464 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
* support mtp logprob
* fix unitest
2025-10-20 15:18:12 +08:00
f1b5392e20
[Intel HPU] Support intel hpu platform ( #4161 )
...
* [Intel HPU] Support intel hpu platform
* fix some issues
* apply precommit and move AttentionBackend_HPU
* fix format issue
* correct ops import
* fix ci issue
* update code in layers
* fix code style issue
* remove dense tp moe ep mode
* fix enc_dec_block_num
* fix rebase issue
* rename hpu to gaudi in readme
* rename ForwardMeta_HPU to HPUForwardMeta
2025-09-24 12:27:50 +08:00
5585cf7aa5
fix mtp_rej_topp input ( #3450 )
2025-08-18 16:12:42 +08:00
f0f00a6025
[OPs] Universal optimization and Fix early_stop cuda 700 ( #3375 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* delete nonzero
* delete setup_ops_base.py
* check if
* check gcp infer_seed.cpu()
* fix repetition_early_stopper_kernel cuda 700
2025-08-14 22:40:44 +08:00
b4fef2cf29
[MetaxGPU] Support FastDeploy on metax gpu ( #3241 )
...
* [MetaxGPU] Support FastDeploy on metax gpu
* Update metax_worker.py
1. change worker log;
2. remove custom allreduce, adapt it later;
3. remove cuda graph;
* Update __init__.py
1. remove metax's key work comment
* Update __init__.py
1. remove metax's key word comment;
2. add fused_moe_kernel_paddle import
---------
Co-authored-by: yongqiangma <xing.wo@163.com >
2025-08-13 11:11:54 +08:00
fbdd6b0663
[Iluvatar GPU] Optimze attention and moe performance ( #3234 )
2025-08-08 10:51:24 +08:00
0fb37ab7e4
update flake8 version to support pre-commit in python3.12 ( #3000 )
...
* update flake8 version to support pre-commit in python3.12
* polish code
2025-07-24 01:43:31 -07:00
2c6a9e887e
native top_p_sampling ( #2901 )
2025-07-22 14:09:59 +08:00
67990e0572
[Feature] support min_p_sampling ( #2872 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Fastdeploy support min_p
* add test_min_p
* fix
* min_p_sampling
* update
* delete vl_gpu_model_runner.py
* fix
* Align usage of min_p with vLLM
* fix
* modified unit test
* fix test_min_sampling
* pre-commit all files
* fix
* fix
* fix
* fix xpu_model_runner.py
2025-07-20 23:17:59 -07:00
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +08:00
1f15ca21e4
[Feature] support prompt repetition_penalty ( #2806 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-17 12:05:52 +08:00
7cdd8d290d
[MTP] optimize mtp infer speed ( #2840 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-14 19:50:22 +08:00
240d6236bc
[Fix]fix top_k_top_p sampling ( #2801 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* fix topk-topp
* update
* add base_non_truncated
2025-07-10 22:35:10 +08:00
1e2319cbef
Rename top_p_sampling to top_k_top_p_sampling ( #2791 )
2025-07-10 00:09:25 -07:00
e45050cae3
[Feature] support top_k_top_p sampling ( #2753 )
...
* support top_k_top_p sampling
* fix
* add api param
* add api para
* fix
* fix
* fix
* fix
* fix
* fix
* fix
2025-07-09 20:58:58 -07:00
d0f4d6ba3a
[GCU] Support gcu platform ( #2702 )
...
baseline: e7fa57ebaexing.wo@163.com >
2025-07-08 13:00:52 +08:00
1b54a2831e
Adapt for iluvatar gpu ( #2684 )
2025-07-07 16:53:14 +08:00
92c2cfa2e7
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
684703fd72
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
sunxin