61789febb9
[Quantization] Support to load static quant ue8m0 scale of DeepGEMM via v0_loader ( #6433 )
...
* support to load static quant ue8m0 scale of deepgemm via v0_loader
* [Fix] Fix ue8m0 scale pack dimension calculation and block size validation
1. Fix pack dimension calculation in fused_moe_triton_backend.py:
- Changed from `ceil_div(...) // 4` to `(num_scales + 3) // 4` for correct ceiling division
- This ensures sufficient pack allocation when num_scales is not a multiple of 4
2. Fix block size hardcoding in block_wise_fp8.py:
- Use `self.quant_config.weight_block_size` instead of hardcoded `[128, 128]`
- Add assertion to ensure weight_block_size is `[128, 128]` for ue8m0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-03 11:32:35 +08:00
22566168c3
[Feature] support qkv&gate linear fusion ( #6455 )
...
* [Feature] support qkv&gate linear fusion
* add test
2026-02-24 15:20:29 +08:00
0eb87467f8
[BugFix]fix RL bug about blockwisefp8 ( #6466 )
...
* fix RL bug about blockwisefp8
* fix moe same bug
* fix RL FP8 bug
2026-02-12 09:15:29 +08:00
9bcd863902
[Others] support import deepgemm/deepep from fleet ops ( #6351 )
...
* update paddleformers to v1.0
* only change import fleetpath
2026-02-09 11:53:13 +08:00
36547cfdb3
[Feature] FD_USE_PHI_FP8_QUANT ( #6320 )
...
* add ut
* add use_fd_quant env
* rm mask_per_token_quant
* add make ops list
* USE_FD_FP8_QUANT -> FD_USE_PHI_FP8_QUANT 默认是true
* modify comments
* use bool type
* Add function declaration
2026-02-03 22:33:03 -08:00
c745a22420
[Feature] Support Ernie FP8 on sm100 ( the fixed version) ( #6304 )
2026-02-03 17:47:38 +08:00
6c685c9474
Revert "[Feature] Support Ernie FP8 on sm100 ( #5593 )" ( #6275 )
...
This reverts commit eb80724b71
2026-01-30 11:22:01 +08:00
eb80724b71
[Feature] Support Ernie FP8 on sm100 ( #5593 )
...
* Deepgemm暂时可用版本
* dense部分 e8m0 ok
* EB模型E8M0跑通的版本
* code check
* support 21b-tp2, dev_paddle
* 单机4.5T ep OK的版本
* 修复删除的代码,单机4.5T ep(非cudagraph)
* eb tp
* Support SM100 block-wise FP8 inference
* refine codes, support deepgemm on sm100
* add thirdparty PFCC/DeepGEMM
* fix ep decode
* 使用deepep ue8m0, 解决精度问题
* 修复FP8 TP精度
* Deepgemm升级适配Hopper逻辑
* add ue8m0 kernel
* add ue8m0 kernel
* fix custom_ops/gpu_ops/cpp_extensions.cc
* eb 输出正常
* eb5 text is right
* 目测精度一致
* 自测精度对齐
* 替换masked_per_token_quant, ep精度OK
* 性能提升约30%
* 暂时跑通ep但是有问题
* 自测一致
* rm test fun
* fix ep event
* 图优化算子更新Deepgemm
* fix build
* 暂时绕过deepgemm CI编译问题
* 根据SM区分deepgemm版本
* remove useless code
---------
Co-authored-by: ckl117 <ckl117@163.com >
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com ”>
Co-authored-by: fxyfxy777 <fxyfxy777@163.com >
2026-01-29 13:49:54 +08:00
4c92035f2d
[Feature] Unify fp8 block_wise quant ops ( #5991 )
...
* quant stash
* blockwise_quant
* precommit
* rm tensor.cut
* tp ok
* add swiglu
* rm outdate code
* fix activate ut
* change baseline
* fix baseline error
2026-01-15 05:50:37 -08:00
11227e00bb
[GraphOptimization] Wrap deep gemm and triton as python op ( #5673 )
...
* [GraphOptimization] Wrap deep gemm and triton as python op
* add unitest to _base_test && compatibility
* paddle.static.MetaTensor -> "paddle.static.MetaTensor"
* mv register_custom_python_op
* rename yaml
---------
Co-authored-by: DrRyanHuang <zihaohuang@aliyun.com >
2025-12-24 15:23:46 +08:00
d8587e987e
[Model] tp+ep support v1_loader ( #5465 )
...
* [Model] tp+ep support v1_loader
* fix
* fix mtp_linear
* fix mtp_linear
* fix
* fix
* fix v0 loader
* fix
* Add get_tensor for ep
* fix linear weight_loader
* fix typo
* fix
2025-12-18 14:31:54 +08:00
b09ebb2813
refactor pt loading ( #4532 )
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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
2025-11-11 21:30:39 +08:00
3dc0ffa46d
[TSP] Support qwen3 moe tsp + cudagraph ( #4871 )
...
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 qwen3_moe tsp mode
* fix
* fix
* update
* update
* update
* fix
* support external_rmsnorm
* update
* fix
2025-11-10 23:37:51 +08:00
29ed617f0f
[v1 loader]qwen Offline fp8 ( #4036 )
...
* support offline fp8
* update ut
* update ut
* update ut
* fix
* update
* update
2025-09-15 13:44:11 +08:00
17b414c2df
MoE Default use triton's blockwise fp8 in TP Case ( #3678 )
2025-08-29 11:07:30 +08:00
3200a80de3
[v1 loader]support fp8 ( #3593 )
...
* support fp8
* update ci
2025-08-26 02:42:46 -07:00
9afa236e39
[NewFeatures] support eplb ( #3547 )
...
* [NewFeatures] support eplb
* fix eplb
2025-08-26 16:19:30 +08:00
9408e667a5
[bugfix]fix blockwisefp8 and all_reduce ( #3243 )
...
* fix
* update
* fix linear for prequant loader
2025-08-06 23:54:33 +08:00
20839abccf
qwen3_moe ( #3084 )
2025-08-06 14:45:27 +08:00
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +08:00
61b3997b85
refactor rl get_name_mappings_to_training ( #2847 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* refactor rl get_name_mappings_to_training
* fix tp>1
* change variable name(ffn1->up_gate_proj/ffn2->down_proj)
* change variable name(linear_weight->weight/linear_bias->bias)
* add rl names mapping for vl
* fix ernie 0.3B error
* fix develop code
* fix
2025-07-15 07:31:42 -07:00
888780ffde
[Feature] block_wise_fp8 support triton_moe_backend ( #2767 )
2025-07-09 19:22:47 +08:00
92c2cfa2e7
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
RichardWooSJTU