Files

T

b8336c3c7c [Bugfix][V1] Split V2 model-runner attention groups on num_heads_q (#45564 )

Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

2026-06-14 21:49:46 -07:00

metrics

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

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

[Perf] Use bisect for mm feature lookup in model runner v2 (#45566 )

2026-06-14 00:22:53 -07:00

model_states

[Model] Add DiffusionGemma Support (#45163 )

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

pool

[Frontend] Re-enable running MaxSim on GPU (#38620 )

2026-04-03 00:03:13 +08:00

sample

[Model Runner V2] Fix openai.InternalServerError: Error code: 500 - 'list index out of range' (#45467 )

2026-06-13 01:44:16 -07:00

spec_decode

[Model] Add DiffusionGemma Support (#45163 )

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

__init__.py

GPU Model Runner V2 (#25266 )

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

async_utils.py

[BugFix][MRV2] Fix cuda event reuse race (#39115 )

2026-04-07 00:21:09 +00:00

attn_utils.py

[Bugfix][V1] Split V2 model-runner attention groups on num_heads_q (#45564 )

2026-06-14 21:49:46 -07:00

block_table.py

[ModelRunnerV2][Hybrid model] Support kernel block size in hybrid model (#38831 )

2026-05-28 00:55:55 +00:00

buffer_utils.py

[ModelRunnerV2] Avoid pipeline parallel bubbles (#42187 )

2026-06-02 14:02:01 -07:00

cp_utils.py

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

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

cudagraph_utils.py

[Bug Fix][Model Runner V2][Spec Decode] Warmup & capture with different attention states for speculator prefill (#44253 )

2026-06-03 13:32:40 -07:00

dp_utils.py

[Refactor] Remove unused dead code (#40640 )

2026-04-25 07:28:18 +08:00

eplb_utils.py

[Bugfix] Unwrap VLM wrappers for EPLB on Model Runner V2 (#42706 )

2026-05-16 07:20:33 +08:00

input_batch.py

[Model] Add DiffusionGemma Support (#45163 )

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

kv_connector.py

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

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

lora_utils.py

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

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

model_runner.py

[Core] Simplify MRV2 async output handling (#45442 )

2026-06-13 18:15:36 -07:00

pp_utils.py

[ModelRunnerV2] Avoid pipeline parallel bubbles (#42187 )

2026-06-02 14:02:01 -07:00

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

[ModelRunnerV2] Avoid pipeline parallel bubbles (#42187 )

2026-06-02 14:02:01 -07:00

structured_outputs.py

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

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

warmup.py

[Model] Add DiffusionGemma Support (#45163 )

2026-06-11 22:17:35 -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.