iHore/vLLM

Files

T

History

251f7e478e [Model] Add PW CUDA graph support for Inkling [2/N] (#48822 )

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
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>

2026-07-16 10:28:56 -07:00

..

[Model Runner V2] Support num NaNs in logits (#30187 )

2025-12-09 10:00:49 -08:00

[ModelRunner V2] Support realtime embeddings (#46762 )

2026-06-26 19:42:27 -07:00

[Model] Add PW CUDA graph support for Inkling [2/N] (#48822 )

2026-07-16 10:28:56 -07:00

[Core] Move MRV1 late_interaction_runner.py out of MRV2 subtree (#48014 )

2026-07-08 18:30:11 +00:00

[Spec Decode] DSpark (#46995 )

2026-07-01 08:30:24 -07:00

[Model] Add PW CUDA graph support for Inkling [2/N] (#48822 )

2026-07-16 10:28:56 -07:00

__init__.py

GPU Model Runner V2 (#25266 )

2025-11-21 08:20:55 -08:00

async_utils.py

[Perf] Use blocking CUDA events to avoid busy polling cuda driver lock (#47081 )

2026-07-07 09:36:10 +00:00

attn_utils.py

[Misc] Use meta tensor for KV cache stride calculation (#47316 )

2026-07-10 23:24:59 -04:00

block_table.py

[PERF] Fuse multi-group block table staged writes (#44944 )

2026-06-16 10:53:27 -07:00

buffer_utils.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424 )

2026-06-20 20:02:24 -07:00

cp_utils.py

[Model Runner V2] Minor simplification for DCP (#34786 )

2026-02-18 11:04:53 -08:00

cudagraph_utils.py

[Model] Add PW CUDA graph support for Inkling [2/N] (#48822 )

2026-07-16 10:28:56 -07:00

dp_utils.py

[Model Runner V2][Bugfix] Fix MRV2 LoRA warmup (#35536 )

2026-06-15 13:17:23 -07:00

eplb_utils.py

[EPLB] Mask padding in EPLB load recording (#38128 )

2026-06-28 19:43:58 -07:00

input_batch.py

[Bugfix] Fix PD disagg + MTP correctness for Qwen3.5(GDN) (#47466 )

2026-07-07 13:51:22 +00:00

kv_connector.py

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

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

lora_utils.py

[Model Runner V2][Bugfix] Fix MRV2 LoRA warmup (#35536 )

2026-06-15 13:17:23 -07:00

model_runner.py

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

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

pp_utils.py

[XPU] Fix PP accuracy on XPU device (#47253 )

2026-07-07 09:17:27 +08:00

README.md

GPU Model Runner V2 (#25266 )

2025-11-21 08:20:55 -08:00

shutdown.py

[MRV2] Add shutdown() method (#41297 )

2026-05-02 21:06:30 -07:00

states.py

[Bugfix] Fix PD disagg + MTP correctness for Qwen3.5(GDN) (#47466 )

2026-07-07 13:51:22 +00:00

structured_outputs.py

[ModelRunner V2] Misc minor simplifications and optimizations (#33467 )

2026-02-01 22:17:14 +00:00

warmup.py

[ModelRunner V2] Warmup cross-attn properly in encoder-decoder case (#47308 )

2026-07-01 12:36:48 -07:00

README.md

[Experimental] Model Runner V2

This directory contains the new model runner which is under active development. Ping Woosuk Kwon for any changes.