Ryan dda27e50f5 [Graph Optimization] remove static_op_get_block_shape_and_split_kv_block from cudagraph (#6081) ...

* rm static_op_get_block_shape_and_split_kv_block from cudagraph

* update max_capture_shape

* fallback: zeros -> empty to avoid coverage check

* check graph_opt_config exists

* add max_capture_shape_dy2st && full_cuda_graph: false -> true in 28B vl test

* add use_cudagraph flag to control step_use_cudagraph

2026-01-20 14:05:18 +08:00

..

batch_invariant

[Deterministic] Move paddle version batch invariant pkg to Fastdeploy (#4763)

2025-12-01 11:25:48 +08:00

benchmarks

[CI]Fix test cases failing under Python 3.12 (#6059)

2026-01-19 15:41:12 +08:00

cache_manager

[BugFix] fix eb5 prefix bug (#5879)

2026-01-06 23:50:39 -08:00

ce

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

ci_use

[Feature] Support stopping the inference for the corresponding request in the online service after a disconnection request. (#5320)

2026-01-16 11:46:13 +08:00

distributed

initial commit (#6054)

2026-01-16 10:49:38 +08:00

e2e

[Graph Optimization] remove static_op_get_block_shape_and_split_kv_block from cudagraph (#6081)

2026-01-20 14:05:18 +08:00

engine

[BugFix] Fix insert_zmq_task_to_scheduler break bug (#5960)

2026-01-12 19:21:01 -08:00

entrypoints

[Feature] Support stopping the inference for the corresponding request in the online service after a disconnection request. (#5320)

2026-01-16 11:46:13 +08:00

eplb

[FDConfig] disable chunked_mm_input in ernie5 (#5774)

2025-12-26 15:31:27 +08:00

graph_optimization

[Graph Optimization] Add full_cuda_graph to control subgraph split (#6027)

2026-01-14 11:43:59 +08:00

input

[Models] Add Qwen3-VL Model Support (#5763)

2025-12-29 17:39:33 +08:00

inter_communicator

[Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868)

2025-12-09 10:53:40 +08:00

layers

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

logger

[Log] Add trace log and add loggingInstrumentor tool (#4692)

2025-11-17 11:08:57 +08:00

metax_ci

[Metax][CI] remove 28B VL model test sampling randomness (#6032)

2026-01-14 14:00:41 +08:00

metrics

[log]console log to llm log (#5680)

2025-12-23 10:05:45 +08:00

model_executor

[Feature] Add PaddleFormers fallback backend (#5999)

2026-01-19 21:50:50 +08:00

model_loader

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

multimodal

[CI]【Hackathon 9th Sprint No.56】NO.56 功能模块 fastdeploy/multimodal/utils.py 单测补充 (#4954)

2025-11-14 10:37:27 +08:00

operators

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

output

[Feature] Support stopping the inference for the corresponding request in the online service after a disconnection request. (#5320)

2026-01-16 11:46:13 +08:00

platforms

[XPU] move xpu_attn_backend.py to FastDeploy/fastdeploy/model_executor/layers/backends/xpu (#5878)

2026-01-09 16:34:57 +08:00

plugins

[Feature] support pool (#3827)

2025-09-22 14:09:09 +08:00

pooling

[Feature] Support prefill batch inference for pooling models. (#5436)

2025-12-09 16:21:00 +08:00

quantization

[Intel HPU] enable tensor_wise_fp8 (#5324)

2025-12-17 16:45:03 +08:00

reasoning

[Feature]Optimization of Thinking Pattern Framework (#4302)

2025-12-10 16:17:06 +08:00

rl

[CI]【Hackathon 9th Sprint No.14】功能模块 fastdeploy/rl/rollout_model.py 单测补充 (#5552)

2025-12-18 10:57:53 +08:00

scheduler

[CI]【Hackathon 9th Sprint No.55】NO.55 功能模块 fastdeploy/scheduler/local_scheduler.py 单测补充 (#5050)

2025-12-29 12:41:50 +08:00

spec_decode

[Speculative Decoding] Support MTP for GLM-4.5-Air (#6047)

2026-01-16 14:35:24 +08:00

splitwise

[PD Disaggregation] Update usage of pd disaggregation and data parallel (#5742)

2026-01-05 17:51:29 +08:00

trace

[Log] Add trace log and add loggingInstrumentor tool (#4692)

2025-11-17 11:08:57 +08:00

usage

[Feature]Report FD statistical information (#5646)

2026-01-14 17:54:01 +08:00

utils

[FDConfig] disable chunked_mm_input in ernie5 (#5774)

2025-12-26 15:31:27 +08:00

v1

[BugFix] fix mm revert bug (#6061)

2026-01-16 08:13:34 -08:00

worker

[Models] Add Qwen3-VL Model Support (#5763)

2025-12-29 17:39:33 +08:00

xpu_ci

add pd+mtp ci (#6090)

2026-01-19 19:21:24 +08:00

conftest.py

[CI] fix test_model_cache (#4982)

2025-11-12 20:26:49 +08:00

cov_pytest.ini

[CI] Add 4-GPU e2e test job (#6082)

2026-01-19 10:42:14 +08:00

utils.py

[FDConfig] disable chunked_mm_input in ernie5 (#5774)

2025-12-26 15:31:27 +08:00