Files

T

Guan-Ming Chiuandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 457a5f34db [Bugfix][MRV2] Support encoder timing stats in model runner V2 (#50020 )

Signed-off-by: Guan-Ming (Wesley) Chiu <105915352+guan404ming@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-08-12 00:00:49 +08:00

metrics

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

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

[Bugfix][MRV2] Support encoder timing stats in model runner V2 (#50020 )

2026-08-12 00:00:49 +08:00

model_states

[Bugfix][MRV2] Support encoder timing stats in model runner V2 (#50020 )

2026-08-12 00:00:49 +08:00

pool

[ModelRunner v2] Enable decoder token-wise pooling (#50931 )

2026-08-06 22:21:52 +00:00

sample

Bound generation inputs before expensive work (#51447 )

2026-08-11 22:03:50 +08:00

spec_decode

[MRV2][Spec] Fuse AR speculator multi-step decodes back into one CUDA graph (#46849 )

2026-08-11 15:06:22 +08:00

__init__.py

…

async_utils.py

[CI] Detect and fail evals on when NaNs appear in logits (#50323 )

2026-08-04 23:02:58 +00:00

attn_utils.py

[Bugfix][TurboQuant] Add KV quant mode for turboquant (#50533 )

2026-07-31 17:42:32 +00:00

block_table.py

[Model Runner v2] E/P/D disaggregation support (#38390 )

2026-08-04 15:52:23 +00:00

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

[MRV2] Always build attn metadata at capture time (#49364 ) (#49995 )

2026-07-27 17:25:17 +00:00

dp_utils.py

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

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

ec_connector.py

[Model Runner v2] E/P/D disaggregation support (#38390 )

2026-08-04 15:52:23 +00:00

eplb_utils.py

feat: extended EPLB support for Mistral Large 3 and additional MoE backends (#48355 )

2026-08-07 05:32:52 -07:00

input_batch.py

[ModelRunner V2] Minor indexing optimizations (#51210 )

2026-08-06 14:44:13 -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

[BugFix][MRV2] Don't create dummy requests longer than max_model_len (#49751 )

2026-07-27 02:04:20 +00:00

model_runner.py

[Bugfix][MRV2] Support encoder timing stats in model runner V2 (#50020 )

2026-08-12 00:00:49 +08:00

pcp_manager.py

[ModelRunner V2] Minor indexing optimizations (#51210 )

2026-08-06 14:44:13 -07:00

pp_utils.py

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

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

README.md

…

shutdown.py

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

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

states.py

[Model Runner V2][Spec Decode] Add multi-layer MTP speculator (#48892 )

2026-07-30 15:54:15 -07:00

structured_outputs.py

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

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

warmup.py

[Bugfix][MRV2] Reserve spec-decode lookahead blocks in V2 warmup (#51438 )

2026-08-08 23:58:43 +00:00

README.md

[Experimental] Model Runner V2

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