Artem Perevedentsev 2cd6c664c1 [MoE] enable all2all fi_one_sided by default (#53311) ...

Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>

2026-08-26 17:03:45 +05:00

..

__init__.py

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

attention.py

[MISC] Cleanup deprecated parameters (#53559)

2026-08-24 10:19:04 -07:00

cache.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

compilation.py

[Kernel][Perf] Add fused CUDA post-conv MTP decode kernel for Qwen3.5 GDN (#51674)

2026-08-14 11:44:45 +08:00

device.py

platforms: add uses_cpu_device() hook to Platform for DeviceConfig (#42313)

2026-05-12 12:39:17 -07:00

diffusion.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

ec_manager_config.py

[Core] Configure custom encoder cache managers from VllmConfig (#51251)

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

ec_transfer.py

[EPD] Remove duplicate image preprocessing in EPD and enable preprocess on GPU (#50390)

2026-08-05 15:59:54 -07:00

fault_tolerance.py

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kernel.py

[Model][MoE] DeepSeek-V4: add opt-in FlashInfer moe_ep expert backend (#49636)

2026-08-25 03:35:01 +00:00

kv_events.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

kv_transfer.py

[Connector] Remove P2pNcclConnector (#44854)

2026-06-08 18:58:29 +08:00

load.py

[Migration] Migrate bitsandbytes support to OOT plugin (#43529)

2026-08-09 10:27:31 +08:00

lora.py

[Model] Add Inkling LoRA support [4/N] (#48884)

2026-07-17 09:52:15 +08:00

mamba.py

[Kernel] Add support for Flashinfer Mamba SSU algorithm selection (#50157)

2026-08-04 09:40:23 -07:00

model_arch.py

Fix Gemma 4 for upcoming Transformers version (#49797)

2026-08-10 07:48:26 +00:00

model.py

[Bugfix] Keep grid dims for XD-RoPE models on a prefix-cache hit (#53456)

2026-08-25 01:14:32 +00:00

multimodal.py

[Bugfix] Skip MM processor cache inserts larger than capacity (#53016)

2026-08-20 13:42:50 +00:00

observability.py

[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

2026-08-20 15:42:49 -07:00

offload.py

[offloader] v2: Hide weight onloading latency via prefetching (#29941)

2026-02-25 17:20:59 -08:00

parallel.py

[MoE] enable all2all fi_one_sided by default (#53311)

2026-08-26 17:03:45 +05:00

pooler.py

[Bugfix] Reject removed pooling parameters (#48984)

2026-07-19 05:18:03 -07:00

profiler.py

[Profiler] Add minimal Triton Proton profiling backend (#48789)

2026-08-11 14:51:57 -07:00

quantization.py

[Online quantization] Add online MXFP4 quantization support (#49347)

2026-08-07 12:39:46 -07:00

reasoning.py

[Feat] Support thinking_token_budget in Model Runner V2 (#46727)

2026-08-07 03:36:18 +00:00

scheduler.py

[Misc] Remove old now unsupported max_num_partial_prefills and max_long_partial_prefills (#49244)

2026-07-21 08:52:52 +00:00

speculative.py

[Model] Add Qwen3-Omni DSpark support (#52560)

2026-08-22 15:35:22 -07:00

speech_to_text.py

support hotwords for FunASR model (#39674)

2026-04-22 02:25:06 -07:00

structured_outputs.py

Remove unused disable_fallback field (#36546)

2026-03-09 20:56:54 -07:00

utils.py

[UX] Reject incompatible nested runtime overrides (#49247)

2026-07-24 07:16:22 -07:00

vllm.py

[Config] Delegate PCP compatibility checks to PCP manager (#53853)

2026-08-26 01:16:01 -07:00

weight_transfer.py

[RL] P2P RDT weight sync (#43375)

2026-08-23 09:42:22 -07:00