Ilya MarkovandTyler Michael Smith 6170d47d22 [EPLB] Optimize EPLB with numpy (#29499) ...

Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

2026-01-07 15:21:35 -05:00

..

__init__.py

[Model] Add MiMo-V2-Flash support (#30836)

2025-12-19 17:17:03 +00:00

attention.py

[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315)

2025-12-05 09:48:43 -08:00

cache.py

[refactor] refactor memory constants usage (#31865)

2026-01-07 18:37:31 +00:00

compilation.py

[Docs] Improve malformed exception caused by backslash line continuations (#31694)

2026-01-05 17:51:54 -08:00

device.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

ec_transfer.py

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233)

2025-11-11 18:58:33 -08:00

kv_events.py

[Feature] publisher default set zmq in kv_event config (#26915)

2025-10-22 19:19:33 +00:00

kv_transfer.py

[P/D] KV Load Failure Recovery/Abort Configuration (#26813)

2025-12-10 11:00:52 -08:00

load.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

lora.py

[Misc] Improve error messages for unsupported types and parameters (#30593)

2026-01-07 09:00:16 +00:00

model_arch.py

[Core] Parse vLLM engine required fields from hf_config to model_arch_config (#28454)

2026-01-02 15:13:15 -08:00

model.py

[Quantization][Refactor] Move CPU GPTQ kernel into MP linear (#31801)

2026-01-06 19:10:18 +00:00

multimodal.py

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

observability.py

Add Multimodal Processor Benchmark (#29105)

2026-01-01 19:26:53 -08:00

parallel.py

[EPLB] Optimize EPLB with numpy (#29499)

2026-01-07 15:21:35 -05:00

pooler.py

[Deprecation] Deprecation --convert reward, use --convert embed instead. (#30463)

2025-12-11 10:18:25 +00:00

profiler.py

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

scheduler.py

[Core] Enable async scheduling by default (#27614)

2025-12-29 13:20:55 -07:00

speculative.py

[Core] Parse vLLM engine required fields from hf_config to model_arch_config (#28454)

2026-01-02 15:13:15 -08:00

speech_to_text.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

structured_outputs.py

Reduce validation to a warning (#28749)

2025-12-05 14:02:49 +00:00

utils.py

Use helper function instead of looping through attribute names (#29788)

2025-12-23 17:31:56 +00:00

vllm.py

Change warning in get_current_vllm_config to report caller's line number (#31855)

2026-01-07 03:48:13 +00:00