Joe Runde de4008e2ab

[Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage (#9352) ...

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>

2024-10-17 22:47:27 -04:00

..

async_engine

[Core] renamePromptInputs and inputs (#8876)

2024-09-26 20:35:15 -07:00

basic_correctness

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

compile

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

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

core

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

data

[Bugfix] Fix order of arguments matters in config.yaml (#8960)

2024-10-05 17:35:11 +00:00

distributed

[Model] PP support for embedding models and update docs (#9090)

2024-10-06 16:35:27 +08:00

encoder_decoder

[Encoder decoder] Add cuda graph support during decoding for encoder-decoder models (#7631)

2024-09-17 07:35:01 -07:00

engine

[Frontend] [Neuron] Parse literals out of override-neuron-config (#8959)

2024-10-03 18:02:07 +00:00

entrypoints

[Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage (#9352)

2024-10-17 22:47:27 -04:00

fp8_kv

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)

2024-04-03 14:15:55 -07:00

kernels

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

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

lora

[Misc] Standardize RoPE handling for Qwen2-VL (#9250)

2024-10-16 13:56:17 +08:00

metrics

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

model_executor

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

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

models

Support BERTModel (first encoder-only embedding model) (#9056)

2024-10-17 23:21:01 +00:00

mq_llm_engine

[Core] renamePromptInputs and inputs (#8876)

2024-09-26 20:35:15 -07:00

multi_step

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

multimodal

[Core] Rename input data types (#8688)

2024-10-16 10:49:37 +00:00

plugins/vllm_add_dummy_model

[Model] VLM2Vec, the first multimodal embedding model in vLLM (#9303)

2024-10-16 14:31:00 +08:00

prefix_caching

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

prompt_adapter

[CORE] Adding support for insertion of soft-tuned prompts (#4645)

2024-07-09 13:26:36 -07:00

prompts

[BugFix] Fix input positions for long context with sliding window (#2088)

2023-12-13 12:28:13 -08:00

quantization

[Misc] Directly use compressed-tensors for checkpoint definitions (#8909)

2024-10-15 15:40:25 -07:00

samplers

[core] remove beam search from the core (#9105)

2024-10-07 05:47:04 +00:00

spec_decode

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

tensorizer_loader

[mypy] Misc. typing improvements (#7417)

2024-08-13 09:20:20 +08:00

tokenization

[Core] Allow specifying custom Executor (#6557)

2024-07-20 01:25:06 +00:00

tool_use

[Frontend][Feature] support tool calling for internlm/internlm2_5-7b-chat model (#8405)

2024-10-04 10:36:39 +08:00

tpu

[torch.compile] integration with compilation control (#9058)

2024-10-10 12:39:36 -07:00

tracing

[misc] hide best_of from engine (#9261)

2024-10-10 21:30:44 -07:00

weight_loading

[Bugfix] Fix Weight Loading Multiple GPU Test - Large Models (#9213)

2024-10-10 14:15:40 +08:00

worker

[Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage (#9352)

2024-10-17 22:47:27 -04:00

__init__.py

[Small] Formatter only checks lints in changed files (#1528)

2023-10-31 15:39:38 -07:00

conftest.py

[Model] VLM2Vec, the first multimodal embedding model in vLLM (#9303)

2024-10-16 14:31:00 +08:00

test_cache_block_hashing.py

[CI/Build] Update Ruff version (#8469)

2024-09-18 11:00:56 +00:00

test_config.py

[Misc] Standardize RoPE handling for Qwen2-VL (#9250)

2024-10-16 13:56:17 +08:00

test_embedded_commit.py

[CI/Build] use setuptools-scm to set __version__ (#4738)

2024-09-23 09:44:26 -07:00

test_inputs.py

[Core][Frontend] Add Support for Inference Time mm_processor_kwargs (#9131)

2024-10-08 14:12:56 +00:00

test_logger.py

[CI/Build] Update Ruff version (#8469)

2024-09-18 11:00:56 +00:00

test_logits_processor.py

[Core] Factor out common code in SequenceData and Sequence (#8675)

2024-09-21 02:30:39 +00:00

test_regression.py

Bugfix: fix broken of download models from modelscope (#5233)

2024-06-06 09:28:10 -07:00

test_sampling_params.py

[Bugfix] fix crash if max_tokens=None (#2570)

2024-01-23 22:38:55 -08:00

test_scalartype.py

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

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

test_sequence.py

[Core] Factor out common code in SequenceData and Sequence (#8675)

2024-09-21 02:30:39 +00:00

test_sharded_state_loader.py

[CI] Upgrade codespell version. (#5381)

2024-06-12 10:06:14 -07:00

test_utils.py

[Core][Frontend] Add Support for Inference Time mm_processor_kwargs (#9131)

2024-10-08 14:12:56 +00:00

utils.py

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00