Michael Goin f83feccd7f

[Bugfix] Ignore GPTQ quantization of Qwen2-VL visual module (#10169) ...

Signed-off-by: mgoin <michael@neuralmagic.com>

2024-11-09 03:36:46 +00:00

..

adapter_commons

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

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

assets

[CI/Build] Update CPU tests to include all "standard" tests (#5481)

2024-11-08 23:30:04 +08:00

attention

[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)

2024-11-07 08:15:14 -08:00

compilation

[Bugfix] SymIntArrayRef expected to contain concrete integers (#10170)

2024-11-08 14:44:18 -08:00

core

[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)

2024-11-07 08:15:14 -08:00

distributed

[Bugfix][XPU] Fix xpu tp by introducing XpuCommunicator (#10144)

2024-11-08 09:41:03 +00:00

engine

[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)

2024-11-07 08:15:14 -08:00

entrypoints

Online video support for VLMs (#10020)

2024-11-07 20:25:59 +00:00

executor

[Misc] Fix ImportError causing by triton (#9493)

2024-11-08 05:08:51 +00:00

inputs

[Misc] Consolidate ModelConfig code related to HF config (#10104)

2024-11-07 06:00:21 +00:00

logging_utils

Rename vllm.logging to vllm.logging_utils (#10134)

2024-11-08 20:53:24 +00:00

lora

[CI/Build] drop support for Python 3.8 EOL (#8464)

2024-11-06 07:11:55 +00:00

model_executor

[Bugfix] Ignore GPTQ quantization of Qwen2-VL visual module (#10169)

2024-11-09 03:36:46 +00:00

multimodal

[0/N] Rename MultiModalInputs to MultiModalKwargs (#10040)

2024-11-09 11:31:02 +08:00

platforms

[Hardware][Intel-Gaudi] Add Intel Gaudi (HPU) inference backend (#6143)

2024-11-06 01:09:10 -08:00

plugins

[3/N] model runner pass the whole config to model (#9958)

2024-11-02 12:08:49 -07:00

profiler

[misc] CUDA Time Layerwise Profiler (#8337)

2024-10-17 10:36:09 -04:00

prompt_adapter

[CI/Build] drop support for Python 3.8 EOL (#8464)

2024-11-06 07:11:55 +00:00

spec_decode

[0/N] Rename MultiModalInputs to MultiModalKwargs (#10040)

2024-11-09 11:31:02 +08:00

transformers_utils

Fix edge case Mistral tokenizer (#10152)

2024-11-08 15:42:27 +00:00

triton_utils

[XPU] avoid triton import for xpu (#9440)

2024-10-24 05:14:00 +00:00

usage

mypy: check additional directories (#9162)

2024-10-08 22:08:22 +00:00

v1

[V1] Fix non-cudagraph op name (#10166)

2024-11-08 10:23:04 -08:00

vllm_flash_attn

[ci][build] fix vllm-flash-attn (#8699)

2024-09-21 23:24:58 -07:00

worker

[0/N] Rename MultiModalInputs to MultiModalKwargs (#10040)

2024-11-09 11:31:02 +08:00

__init__.py

[Core] renamePromptInputs and inputs (#8876)

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

_custom_ops.py

[Kernel][Triton] Add Triton implementation for scaled_mm_triton to support fp8 and int8 SmoothQuant, symmetric case (#9857)

2024-11-08 19:59:22 -05:00

_ipex_ops.py

[Misc][XPU] Upgrade to Pytorch 2.5 for xpu backend (#9823)

2024-11-06 17:29:03 -08:00

beam_search.py

[Frontend] re-enable multi-modality input in the new beam search implementation (#9427)

2024-10-29 11:49:47 +00:00

block.py

[mypy] Enable mypy type checking for vllm/core (#7229)

2024-08-28 07:11:14 +08:00

config.py

Disable spec-decode + chunked-prefill for draft models with tensor parallelism > 1 (#10136)

2024-11-08 15:56:18 +00:00

connections.py

[core][distributed] fix zmq hang (#6759)

2024-07-24 17:37:12 -07:00

envs.py

[torch.compile] Fuse RMSNorm with quant (#9138)

2024-11-08 21:20:08 +00:00

forward_context.py

[misc] add forward context for attention (#9029)

2024-10-03 12:09:42 -07:00

logger.py

Rename vllm.logging to vllm.logging_utils (#10134)

2024-11-08 20:53:24 +00:00

logits_process.py

[Frontend] Bad words sampling parameter (#9717)

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

outputs.py

[core] move parallel sampling out from vllm core (#9302)

2024-10-22 00:31:44 +00:00

pooling_params.py

[Frontend] Chat-based Embeddings API (#9759)

2024-11-01 08:13:35 +00:00

py.typed

Add py.typed so consumers of vLLM can get type checking (#1509)

2023-10-30 14:50:47 -07:00

sampling_params.py

[Bugfix][Frontend] Reject guided decoding in multistep mode (#9892)

2024-11-01 01:09:46 +00:00

scalar_type.py

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

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

scripts.py

[Frontend] Add Early Validation For Chat Template / Tool Call Parser (#9151)

2024-10-08 14:31:26 +00:00

sequence.py

[Core] Make encoder-decoder inputs a nested structure to be more composable (#9604)

2024-11-05 10:07:31 +08:00

tracing.py

[misc] hide best_of from engine (#9261)

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

utils.py

[Misc] Consolidate ModelConfig code related to HF config (#10104)

2024-11-07 06:00:21 +00:00

version.py

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

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