Isotr0py be8a72f0a6 Stack torch.compile with CUDA graph decode instead of choosing one ...

Regionally compile the DiT blocks even when enable_cuda_graph_decode is set
and let graph capture record the compiled (fused) kernels; inductor's own
cudagraphs stay off so the two graph layers never nest. Measured on GB200
(1024x1024, 50 steps, seed 42, BF16): combo 3.04s vs compile-only 3.2s,
graph-only 4.0s, eager 4.3s per image; 44.5-45.6 dB PSNR vs eager.

2026-09-22 08:58:32 +00:00

..

attention

[BugFix][NPU] Fix Fish Speech S2 Pro NPU support (#7546)

2026-09-16 11:38:06 -07:00

benchmarks

[Model] Integrate AURA into Full-Duplex Runtime (#7633)

2026-09-21 09:26:54 -07:00

clients

[Bugfix] Refresh duplex client defaults after session updates (#7784)

2026-09-21 16:24:42 +00:00

config

Merge branch 'main' into qwen-image-2.1

2026-09-22 10:11:12 +08:00

core

[Bugfix] Add opt-in MiniCPM-o 4.5 Stage-0 sliding window (#7631)

2026-09-21 18:34:22 -07:00

deploy

[Model] MammothModa2: enable Cache-DiT acceleration for the DiT stage (#7291)

2026-09-21 18:34:12 -07:00

diffusion

Stack torch.compile with CUDA graph decode instead of choosing one

2026-09-22 08:58:32 +00:00

distributed

[Core][Diffusion] Add pause_generation(mode="keep") for diffusion stages (#7685)

2026-09-22 01:31:22 +08:00

engine

Merge branch 'main' into qwen-image-2.1

2026-09-22 10:11:12 +08:00

entrypoints

Merge branch 'main' into qwen-image-2.1

2026-09-22 10:11:12 +08:00

experimental

[LingBot World] Eleven bit-identical removals of repeated work in the realtime path (#7648)

2026-09-21 06:12:45 +00:00

host_weight_runtime

[Bugfix][Core] Clean up failed HWR atomic metadata writes (#6956)

2026-09-11 09:03:26 +08:00

inputs

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759)

2026-09-15 20:43:30 -07:00

lora

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

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

metrics

[Bugfix] Register statistics for dynamically added replicas (#7298)

2026-09-19 17:07:14 +00:00

model_executor

[CI][ROCm] Shorten the blocking CosyVoice test path (#7748)

2026-09-21 18:34:40 -07:00

model_extras

Address review: examples policy, SPDX headers, recipe docs, test coverage

2026-09-21 08:36:42 +00:00

outputs

[Core][Model] Enable Qwen3-TTS MRV2 and optimize the TTS pipeline (#7781)

2026-09-20 23:03:08 -07:00

platforms

[Performance] Capture MOSS-TTS codec streaming decode with NPUGraph (#7280)

2026-09-21 06:38:23 +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

protocol

[Model] Integrate AURA into Full-Duplex Runtime (#7633)

2026-09-21 09:26:54 -07:00

quantization

[Bugfix][Ascend NPU][Diffusion] Load over-wide unquantized fallback weights straight into host memory under DLOFix/mxfp online offload after quant (#7009)

2026-09-18 07:36:48 +00:00

reasoning

[Rebase] Rebase to vLLM 0.29.0 (#7230)

2026-09-10 12:08:28 +08:00

sample

update dirs

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

tokenizers

[Fix] Restore MammothModa2 support (#6694)

2026-08-28 08:32:32 +08:00

transformers_utils

[Misc] Remove Dynin-Omni and dots.tts support (#7655)

2026-09-20 00:28:29 -07:00

utils

[Frontend] Scale Omni serving across API processes (#6923)

2026-09-16 22:29:31 -07:00

worker

[Perf][Qwen3-TTS] Enable event-driven orchestration by default (#7088)

2026-09-21 12:09:19 -07:00

worker_v2

[Core][Model] Enable Qwen3-TTS MRV2 and optimize the TTS pipeline (#7781)

2026-09-20 23:03:08 -07:00

__init__.py

[Rebase] Rebase to vllm 0.26.0 (#5443)

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

data_entry_keys.py

[Core][Model] Enable Qwen3-TTS MRV2 and optimize the TTS pipeline (#7781)

2026-09-20 23:03:08 -07:00

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

[Rebase] Rebase to vllm 0.28.0 (#6606)

2026-08-27 06:12:55 +00:00

version.py

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

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