JooHo Lee a045c7425f [MM][CG] Profile encoder CUDA graph pool memory (#41714) ...

Signed-off-by: JooHo Lee <jooho414@gmail.com>

2026-06-02 12:27:34 +08:00

..

cpu

[CPU] Experimentally enable Triton and MRV2 (#43225)

2026-05-22 01:48:17 -07:00

gpu

[MRV2] Remove Eagle's dedicated CUDA graph pool (#44078)

2026-05-31 22:00:33 -07:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_table.py

[Bugfix] Align block table for TRTLLM MLA edge-case (#39324)

2026-05-06 11:17:02 -07:00

cp_utils.py

[Bug] Fix dcp error message (#40053)

2026-04-20 10:52:32 -04:00

cpu_model_runner.py

[BugFix][CPU][Spec Decode] Fix Eagle implementation on CPU backend (#42468)

2026-05-19 03:16:07 +00:00

cpu_worker.py

[CPU] Experimentally enable Triton and MRV2 (#43225)

2026-05-22 01:48:17 -07:00

dp_utils.py

[Perf][1/n] Eliminate various GPU<->CPU syncs (#41429)

2026-05-11 20:36:03 +00:00

ec_connector_model_runner_mixin.py

[Refactor] Remove dead code in kv connector and model runner (#38383)

2026-03-31 17:05:23 -04:00

encoder_cudagraph_defs.py

Adjust design around encoder_cudagraph_forward (#42288)

2026-05-29 03:02:52 +00:00

encoder_cudagraph.py

[MM][CG] Profile encoder CUDA graph pool memory (#41714)

2026-06-02 12:27:34 +08:00

gpu_input_batch.py

[Perf] Avoid forward scan for async output placeholders (#42938)

2026-05-19 20:16:07 -07:00

gpu_model_runner.py

[MM][CG] Profile encoder CUDA graph pool memory (#41714)

2026-06-02 12:27:34 +08:00

gpu_ubatch_wrapper.py

[Bugfix] V1: support tuple model outputs in ubatch wrapper (dbo + spec decode) (#40789)

2026-05-13 15:47:51 -07:00

gpu_worker.py

[Frontend][Core] Add sparse NCCL weight transfer support for in-place updates (#40096)

2026-06-01 15:37:30 -04:00

kv_connector_model_runner_mixin.py

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

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

lora_model_runner_mixin.py

[Bugfix] LoRA for DeepSeek V3.2 (#35077)

2026-04-22 19:33:50 +08:00

mamba_utils.py

[Perf] [Hybrid] Fused Triton kernel for GPU-side Mamba state postprocessing (#40172)

2026-05-21 04:50:54 -07:00

tpu_input_batch.py

[Cleanup] Remove unused ModelRunner V1 InputBatch.num_tokens field (#30218)

2025-12-18 09:17:00 -08:00

ubatch_utils.py

[BugFix] Preserve max_seq_len in ubatch metadata during CUDA graph capture (#40961)

2026-05-05 04:29:34 +00:00

ubatching.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

utils.py

[Model Runner V2] Support sharing kv cache layers (#35045)

2026-05-22 22:18:23 +00:00

worker_base.py

[Perf] Set IR Op Priority Once at Worker Init (#42631)

2026-05-15 15:56:13 +00:00

workspace.py

[Bugfix] Fix workspace resize leaking reserved GPU memory (#39226)

2026-04-23 20:50:05 +00:00

xpu_model_runner.py

[Refactor] Remove dead code in kv connector and model runner (#38383)

2026-03-31 17:05:23 -04:00

xpu_worker.py

[MRV2][XPU] add Model Runner V2 log (#42710)

2026-05-17 04:15:50 +00:00