3 people 6853d7204d [Bugfix] Add single-80GB deploy config for MOSS-TTS (resolves #4643 OOM) (#4761) ...

Signed-off-by: Inesh Reddy <ineshreddy249@gmail.com>
Signed-off-by: Inesh Reddy Chappidi <ineshreddy249@gmail.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-07-18 13:49:10 +08:00

..

attention

[Bugfix] Fix Fish Speech kvcache attention KV cache unpacking for vLLM 0.23.0 (#4428)

2026-06-22 09:22:41 +08:00

benchmarks

[Feature] Support MOSS-TTS-Local-v1.5 vocoder graph (#4929)

2026-07-16 15:02:15 +08:00

config

Fix hunyuan ci (#5143)

2026-07-16 14:49:13 +00:00

core

[Rebase] Rebase to vllm v0.25.0 (#5042)

2026-07-12 23:39:53 +08:00

deploy

[Bugfix] Add single-80GB deploy config for MOSS-TTS (resolves #4643 OOM) (#4761)

2026-07-18 13:49:10 +08:00

diffusion

[bugfix] Use FlowMatchEulerDiscreteScheduler from diffusers 0.39.0 with correct RNG handling for upcoming Cosmos3 distilled models (#5176)

2026-07-17 11:38:04 -07:00

distributed

[Bug Fix] Hunyuan image cfg bugfix (#4752)

2026-07-15 13:08:15 +08:00

engine

[Refactor][OutputProcessor 1/8]: clean up multimodal payload accumulation and move payload logic into MultimodalPayload & directory refactor (#4980)

2026-07-15 15:50:19 +08:00

entrypoints

examples: replica data-parallel recipe + benchmark for video DiT (#4707) (#5052)

2026-07-17 03:26:35 +00:00

experimental

[Bugfix] Accept kv_prefetch_jobs in ARDiffusionModelRunner.execute_model (#4941)

2026-07-14 08:22:40 +00:00

inputs

Cosmos3 transfer (#4379)

2026-06-21 09:59:18 +08:00

lora

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

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

metrics

[BugFix][Ming-TTS] Improve Seed-TTS WER accuracy (#4859)

2026-07-03 12:15:03 +02:00

model_executor

[Feature] Support MOSS-TTS-Local-v1.5 vocoder graph (#4929)

2026-07-16 15:02:15 +08:00

model_extras

Add Cosmos3 Edge and Distilled checkpoints support (#5001)

2026-07-16 09:39:40 -07:00

outputs

[Refactor][OutputProcessor 1/8]: clean up multimodal payload accumulation and move payload logic into MultimodalPayload & directory refactor (#4980)

2026-07-15 15:50:19 +08:00

platforms

[Hardware][Ascend][Model] Optimize Qwen3-TTS on 310P (#4841)

2026-07-15 08:57:44 +08:00

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

Fix FP8 Quack GEMM call when inference_mode() and torch.compile() is used. (#5153)

2026-07-16 15:01:21 -07:00

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

Revert "[Bugfix] Use MediaConnector for image/video URL fetching to prevent SSRF" (#4751)

2026-06-27 01:18:48 +08:00

utils

[Bugfix] Fix full-payload mm splitting for dual hidden/scheduled batch axes (#4870 follow-up) (#4910)

2026-07-06 15:08:05 +08:00

worker

[Feature] Support MOSS-TTS-Local-v1.5 vocoder graph (#4929)

2026-07-16 15:02:15 +08:00

__init__.py

[Bugfix][Refactor] Migrate Voxtral TTS config and parser registry (#3065)

2026-04-25 18:17:25 +08:00

data_entry_keys.py

[Perf][TTS] Optimize cosyvoice TTFP and throughput using TensorRT (#4168)

2026-06-10 16:42:34 +08:00

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 v0.25.0 (#5042)

2026-07-12 23:39:53 +08:00

request.py

[Bugfix] Align vLLM Omni Request input signature with vLLM. (#4568)

2026-06-20 04:25:43 +00:00

version.py

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

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