Elfie Guo 9ff4511e43 [Misc] Add chunked-prefill support on FlashInfer. (#9781)

2024-10-30 09:33:53 -07:00

..

async_engine

[MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py (#9510)

2024-10-18 14:30:55 -07:00

basic_correctness

[Misc] Add chunked-prefill support on FlashInfer. (#9781)

2024-10-30 09:33:53 -07:00

compile

[torch.compile] rework compile control with piecewise cudagraph (#9715)

2024-10-29 23:03:49 -07:00

core

[core] simplify seq group code (#9569)

2024-10-24 00:16:44 -07:00

data

[Bugfix] Fix load config when using bools (#9533)

2024-10-27 13:46:41 -04:00

distributed

[torch.compile] Adding torch compile annotations to some models (#9641)

2024-10-24 09:31:42 -07:00

encoder_decoder

[Hardware][CPU] using current_platform.is_cpu (#9536)

2024-10-22 00:50:43 -07:00

engine

[CI/Build] VLM Test Consolidation (#9372)

2024-10-30 09:32:17 -07:00

entrypoints

[Bugfix][Frontend] Guard against bad token ids (#9634)

2024-10-29 14:13:20 -07:00

fp8_kv

…

kernels

[Hardware] using current_platform.seed_everything (#9785)

2024-10-29 14:47:44 +00:00

lora

[Hardware] using current_platform.seed_everything (#9785)

2024-10-29 14:47:44 +00:00

metrics

[BugFix] Fix metrics error for --num-scheduler-steps > 1 (#8234)

2024-10-22 15:43:03 -07:00

model_executor

[torch.compile] Fine-grained CustomOp enabling mechanism (#9300)

2024-10-17 18:36:37 +00:00

models

[CI/Build] VLM Test Consolidation (#9372)

2024-10-30 09:32:17 -07:00

mq_llm_engine

[Frontend] Don't log duplicate error stacktrace for every request in the batch (#9023)

2024-10-21 14:49:41 -07:00

multi_step

…

multimodal

[Model] Add user-configurable task for models that support both generation and embedding (#9424)

2024-10-18 11:31:58 -07:00

plugins/vllm_add_dummy_model

…

prefix_caching

[MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py (#9510)

2024-10-18 14:30:55 -07:00

prompt_adapter

…

prompts

…

quantization

🐛 fix torch memory profiling (#9516)

2024-10-18 21:25:19 -04:00

samplers

[Frontend] Bad words sampling parameter (#9717)

2024-10-26 16:29:38 +00:00

spec_decode

[Hardware][ROCM] using current_platform.is_rocm (#9642)

2024-10-28 04:07:00 +00:00

tensorizer_loader

[MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py (#9510)

2024-10-18 14:30:55 -07:00

tokenization

…

tool_use

[Model] tool calling support for ibm-granite/granite-20b-functioncalling (#8339)

2024-10-29 15:07:37 -07:00

tpu

…

tracing

[BugFix] Prevent exporting duplicate OpenTelemetry spans (#9017)

2024-10-22 11:11:53 -07:00

weight_loading

…

worker

[Hardware][CPU] using current_platform.is_cpu (#9536)

2024-10-22 00:50:43 -07:00

__init__.py

…

conftest.py

[CI/Build] VLM Test Consolidation (#9372)

2024-10-30 09:32:17 -07:00

test_cache_block_hashing.py

…

test_config.py

[Model] Add user-configurable task for models that support both generation and embedding (#9424)

2024-10-18 11:31:58 -07:00

test_embedded_commit.py

…

test_inputs.py

…

test_logger.py

…

test_logits_processor.py

…

test_regression.py

…

test_sampling_params.py

…

test_scalartype.py

[Bugfix] Fix support for dimension like integers and ScalarType (#9299)

2024-10-17 19:08:34 +00:00

test_sequence.py

…

test_sharded_state_loader.py

[CI/Build] Replaced some models on tests for smaller ones (#9570)

2024-10-22 04:52:14 +00:00

test_utils.py

[Bugfix] Fix load config when using bools (#9533)

2024-10-27 13:46:41 -04:00

utils.py

[CI/Build] VLM Test Consolidation (#9372)

2024-10-30 09:32:17 -07:00