3 people de7d70676d [Perf] Low-latency CPU all-reduce for DP metadata syncs (#61767) ...

Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: hjjq <50634613+hjjq@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-15 15:29:13 -07:00

..

cpu

[MRV2] Buffer util simplifications (#56888)

2026-09-15 20:36:51 +00:00

gpu

[Perf] Low-latency CPU all-reduce for DP metadata syncs (#61767)

2026-10-15 15:29:13 -07:00

sentinel

[Bugfix][FT] Pass stateless process-group timeouts explicitly (#58611)

2026-09-29 03:14:02 +00:00

__init__.py

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

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

block_table.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)

2026-10-09 15:48:37 -04:00

cp_utils.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)

2026-10-09 15:48:37 -04:00

cpu_model_runner.py

[Attention] Remove cascade attention (#61126)

2026-10-12 10:41:07 -07:00

cpu_worker.py

[Bugfix][CPU] Report the real cause when the worker outgrows its memory reservation (#59472)

2026-10-15 21:52:05 +08:00

dp_utils.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

ec_connector_model_runner_mixin.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

encoder_cudagraph_defs.py

[MM][CG] Enable encoder CUDA Graph for MiniCPM-V (#42785)

2026-09-10 06:28:48 +00:00

encoder_cudagraph.py

[Multimodal] Optimize encoder cudagraph padding logic (#58925)

2026-10-08 03:38:09 +00:00

gpu_input_batch.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)

2026-10-09 15:48:37 -04:00

gpu_model_runner.py

[Chore] Use upstream Transformers DeepseekV4Config (#61392)

2026-10-15 01:08:08 -07:00

gpu_ubatch_wrapper.py

[ROCm][Perf] Enable DPA+ETP prefill compute/comm dual-batch-overlap for DeepSeek-V4 (#57773)

2026-10-15 11:16:48 +08:00

gpu_worker.py

[MRV2][Spec Decode] Quantized draft lm_head for drafters that share the target head (#59973)

2026-10-15 22:06:40 +00:00

kv_connector_model_runner_mixin.py

[Bugfix][KVConnector] Finalize saves on steps without a forward (#57775)

2026-09-25 00:06:36 +00:00

lora_model_runner_mixin.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

mamba_utils.py

[Bugfix] Index Mamba align state copies by request slot in MRV2 (#60210)

2026-10-07 02:32:46 +00:00

mm_encoder_model_runner.py

[Bugfix][MRV2] Match fast-prefill padding to active LoRA batches (#56456)

2026-09-18 22:13:23 +00:00

startup_plan.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

ubatch_utils.py

[ROCm][Perf] Enable DPA+ETP prefill compute/comm dual-batch-overlap for DeepSeek-V4 (#57773)

2026-10-15 11:16:48 +08:00

ubatching.py

[ROCm][Perf] Enable DPA+ETP prefill compute/comm dual-batch-overlap for DeepSeek-V4 (#57773)

2026-10-15 11:16:48 +08:00

utils.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)

2026-10-09 15:48:37 -04:00

worker_base.py

[Core] Add lifecycle hooks for worker extensions (#59463)

2026-10-13 21:51:05 +08:00

workspace.py

[Bugfix][MoE] Size the permute scratch from its inputs (#60447)

2026-10-08 15:32:07 -04:00

xpu_model_runner.py

[Attention] Remove cascade attention (#61126)

2026-10-12 10:41:07 -07:00

xpu_worker.py

[Refactor] Share workspace and model runner init between GPU and XPU workers (#59200)

2026-09-30 14:29:12 +00:00