Hongsheng Liu 73b623f2f7 [Core] Add Host Weight Runtime foundation (#6419) ...

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-08-21 08:50:59 +08:00

..

attention

[Rebase] Rebase to vllm 0.26.0 (#5443)

2026-07-27 23:35:49 +08:00

benchmarks

[Bugfix][MiniCPM-o] Load Daily-Omni QA metadata from the hub cache (#6276)

2026-08-18 10:53:55 +08:00

config

[Model] Suppress silence codec tokens for the first N Qwen3-TTS decod… (#5048)

2026-08-20 09:22:37 -07:00

core

[Bugfix] Reclaim resumable async-chunk requests on finish (#6360)

2026-08-20 15:59:39 +08:00

deploy

[Model] Suppress silence codec tokens for the first N Qwen3-TTS decod… (#5048)

2026-08-20 09:22:37 -07:00

diffusion

Cosmos3 logging and prompt improvements (#6325)

2026-08-20 12:04:49 -07:00

distributed

[Bugfix] Reclaim resumable async-chunk requests on finish (#6360)

2026-08-20 15:59:39 +08:00

engine

[Bugfix][Core] Fix replica device split when a stage omits devices (#5445)

2026-08-21 00:44:03 +08:00

entrypoints

[Bugfix] Preserve prompt token usage details (#5181)

2026-08-20 20:05:05 +00:00

experimental

[Bugfix][MiniCPM-o] Stop Talker mid-utterance truncation and load cod… (#6346)

2026-08-20 11:50:07 +08:00

host_weight_runtime

[Core] Add Host Weight Runtime foundation (#6419)

2026-08-21 08:50:59 +08:00

inputs

[Model][Feat] Support Minimax-H3 quality grading requests through dynamic loading/unloading with Cache-DiT (#5853)

2026-08-07 09:07:23 +00:00

lora

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

metrics

[Metrics] Add Diffusion Metrics (#4755)

2026-08-13 06:59:13 +00:00

model_executor

[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#5791)

2026-08-20 19:22:40 +00:00

model_extras

Cosmos3 transfer fix (#5614)

2026-08-20 11:40:51 -07:00

outputs

[Bugfix] Carry ec_transfer_params and num_cache_creation_tokens on OmniRequestOutput (#6152)

2026-08-15 08:37:27 +00:00

platforms

[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#5791)

2026-08-20 19:22:40 +00:00

plugins

[Quantization] Migrate GGUF diffusion model support to OOT plugin (#4769)

2026-07-11 18:48:43 +00:00

profiler

[Enhancement]modify profiling.md (#3051)

2026-04-24 16:30:24 +08:00

quantization

[Diffusion][Quantization] Enable MiniMax-H3 global FP8 with DLO (#5910)

2026-08-15 23:01:26 +08:00

reasoning

Step audio R1 reasoning parser (#2846)

2026-06-10 21:03:19 +00:00

sample

update dirs

2025-09-11 15:43:43 +08:00

tokenizers

add support for MammothModa2 model (#336)

2026-03-04 22:52:56 +08:00

transformers_utils

[Bugfix | Model] Fix SenseNova & Use Well-defined Model Configs (#5877)

2026-08-18 16:43:05 +00:00

utils

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

2026-08-12 22:58:23 +08:00

worker

[Model] Suppress silence codec tokens for the first N Qwen3-TTS decod… (#5048)

2026-08-20 09:22:37 -07:00

__init__.py

[Rebase] Rebase to vllm 0.26.0 (#5443)

2026-07-27 23:35:49 +08:00

data_entry_keys.py

[Model] Add MiniMax Music 3 text-to-music (#6186)

2026-08-18 04:33:13 +00:00

errors.py

[refactor] Refactor guardrail error handling - add 400 error code (#4297)

2026-06-11 21:09:24 +00:00

logger.py

[BugFix] Failed to print DEBUG level log (#307)

2025-12-15 07:13:36 +00:00

patch.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

request.py

[New Model] Support IndexTTS 2.5 (#5957)

2026-08-11 23:00:35 +00:00

version.py

[Misc] Warn When vLLM / vLLM-Omni Have Mismatched Versions (#2691)

2026-04-17 20:15:16 +08:00