10 people 166a8e954b [Model] Add Inkling multi-depth MTP support [5/N] ...

Extend the merged Inkling MTP=1 implementation to multiple checkpoint depths with multi-step speculative decoding and KV-cache plumbing.

Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>

2026-07-16 21:17:29 +00:00

..

assets

[Bugfix] Align OpenCV video metadata timeline (#47099)

2026-06-30 20:43:42 +00:00

benchmarks

[Bugfix] Re-enable benchmarking of librispeech dataset. (#47033)

2026-07-08 16:19:26 +00:00

compilation

[Refactor] Move fla to third party (#48500)

2026-07-16 19:22:36 +01:00

config

[Model] Add Inkling multi-depth MTP support [5/N]

2026-07-16 21:17:29 +00:00

cute_utils

[GDN] Improve kkt kernel of CuteDSL prefill backend (#46346)

2026-06-29 18:34:18 -07:00

device_allocator

[Core] Make sleep-mode backend capability flags communicator-agnostic (#47243)

2026-07-01 07:17:44 +00:00

distributed

[Bugfix][KV-transfer] MoRIIO: retry RDMA send-queue-full backpressure instead of failing the read (#47495)

2026-07-16 20:02:27 +00:00

engine

BF16x3 router GEMM (#47973)

2026-07-16 17:04:20 +08:00

entrypoints

[Frontend] Overlap preprocessing and computation for pooling models offline inference (#47699)

2026-07-16 14:00:20 +00:00

inputs

[Render][Speculator] Add return_loss_mask to render endpoint for training data generation (#46846)

2026-06-28 00:07:33 -07:00

ir

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

kernels

[Helion] Fix degenerate scale_ub in kernel input generators (#48868)

2026-07-16 19:57:45 +00:00

logging_utils

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)

2026-03-31 22:15:05 -04:00

lora

fix(lora): validate LoRA rank is positive in PEFTHelper (#48437)

2026-07-16 05:22:52 +00:00

model_executor

[Model] Add Inkling MTP=1 support [3/N] (#48869)

2026-07-16 13:27:21 -07:00

models

[Model] Add Inkling multi-depth MTP support [5/N]

2026-07-16 21:17:29 +00:00

multimodal

[Bugfix][Security] Fix concurrent sparse invariant race bypassing CVE remediation (#48583)

2026-07-14 11:08:24 +00:00

parser

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

platforms

[Bugfix] Fix FlashInfer non-causal draft attention (DFlash/DSpark) on Blackwell (#48167)

2026-07-15 12:44:01 -07:00

plugins

[Frontend] Add endpoint plugins framework (#47454)

2026-07-08 10:00:41 +08:00

profiler

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

ray

[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383)

2026-02-17 01:08:42 -08:00

reasoning

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

renderers

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

third_party

[Refactor] Move fla to third party (#48500)

2026-07-16 19:22:36 +01:00

tokenizers

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

tool_parsers

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

tracing

[Feature] OTEL tracing during loading (#31162)

2026-02-05 16:59:28 -08:00

transformers_utils

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

triton_utils

[ROCm][Bugfix] Fix use_v2_model_runner inside Ray driver thread (#45998)

2026-06-24 08:41:56 +08:00

usage

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

utils

[Model] Add Inkling multi-depth MTP support [5/N]

2026-07-16 21:17:29 +00:00

v1

[Model] Add Inkling multi-depth MTP support [5/N]

2026-07-16 21:17:29 +00:00

vllm_flash_attn

[CI/Build][Docker] Bump nvidia-cutlass-dsl to 4.6.0 and drop packaging workarounds (#47442)

2026-07-16 13:51:41 +00:00

__init__.py

Remove bc-lint (#35274)

2026-02-26 03:01:01 -08:00

_aiter_ops.py

[Doc] Sync four function docstrings with their signatures (#45437)

2026-07-14 13:10:13 -04:00

_custom_ops.py

add pad-aware reduce path (#48385)

2026-07-14 18:05:50 -07:00

_xpu_ops.py

[BUGFIX][XPU] Update fa interface for compatibility (#45394)

2026-06-12 11:45:01 +00:00

collect_env.py

[XPU]Enhance environment collection for Intel XPU and optimize layout (#35698)

2026-04-13 12:51:46 +08:00

connections.py

[CI] Add retry with 4x backoff to HTTP fetches for transient failures (#37218)

2026-03-19 19:00:20 +00:00

env_override.py

[Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425)

2026-06-16 15:16:45 +02:00

envs.py

[KVOffload][P2P] Well-known default host/port env vars and per-DP-rank control port (#47636)

2026-07-15 15:22:56 +03:00

exceptions.py

[Bugfix] Return HTTP 422 for unprocessable image URLs instead of 500 (#47165)

2026-07-06 11:56:23 +00:00

forward_context.py

[Feature] Support sequence parallel without the need for DP, 1.9%~5.0% E2E Throughput Improvement (#47070)

2026-07-05 05:41:30 -07:00

logger.py

[Log] Log once in local node by default (#37568)

2026-03-19 12:04:59 -07:00

logits_process.py

…

logprobs.py

Make mypy opt-out instead of opt-in (#33205)

2026-01-29 09:12:26 +00:00

model_inspection.py

[UX] Add vLLM model inspection view (#29450)

2026-01-09 10:12:35 -07:00

outputs.py

[EC Connector] Add EC Transfer Params (#42433)

2026-07-12 14:35:33 +03:00

pooling_params.py

[Misc] Improve Matryoshka pooling dimensions validation (#48057)

2026-07-13 12:57:36 -04:00

py.typed

…

sampling_params.py

[Frontend] Expose logprob_token_ids on Python OpenAI endpoints (#43463)

2026-07-13 14:40:21 -07:00

scalar_type.py

Humming support for 2/3/5/6/7-bit pack-quantized weight-only inference (#46389)

2026-06-24 13:53:54 -04:00

scripts.py

…

sequence.py

[Core] Cleanup KVConnector handling with PP + fix MRV2 (#43732)

2026-05-28 13:12:03 -07:00

tasks.py

[Frontend] Remove frontend pooling multi task support. (#37861)

2026-04-21 12:27:44 +00:00

version.py

…