Lucas Wilkinson e312e52b44 [Kernel] Add Exllama as a backend for compressed-tensors (#9395)

2024-10-17 09:48:26 -04:00

..

fused_moe

[Kernel] adding fused moe kernel config for L40S TP4 (#9245)

2024-10-11 08:54:22 -07:00

mamba

[Kernel][Model] Improve continuous batching for Jamba and Mamba (#9189)

2024-10-16 12:12:43 -04:00

quantization

[Kernel] Add Exllama as a backend for compressed-tensors (#9395)

2024-10-17 09:48:26 -04:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

activation.py

[Model][Bugfix] Add FATReLU activation and support for openbmb/MiniCPM-S-1B-sft (#9396)

2024-10-16 16:40:24 +00:00

layernorm.py

[Model] Support NVLM-D and fix QK Norm in InternViT (#9045)

2024-10-07 11:55:12 +00:00

linear.py

[Hardware][CPU] Support AWQ for CPU backend (#7515)

2024-10-09 10:28:08 -06:00

logits_processor.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

pooler.py

[Model] Support Qwen2.5-Math-RM-72B (#8896)

2024-09-28 21:19:39 -07:00

rejection_sampler.py

[SpecDec][Misc] Cleanup, remove bonus token logic. (#8701)

2024-09-22 12:34:14 -07:00

resampler.py

[MODEL] Qwen Multimodal Support (Qwen-VL / Qwen-VL-Chat) (#8029)

2024-09-05 12:48:10 +00:00

rotary_embedding.py

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

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

sampler.py

[CI/Build] mypy: Resolve some errors from checking vllm/engine (#9267)

2024-10-16 22:55:59 +00:00

spec_decode_base_sampler.py

[SpecDec][Misc] Cleanup, remove bonus token logic. (#8701)

2024-09-22 12:34:14 -07:00

typical_acceptance_sampler.py

Fix typical acceptance sampler with correct recovered token ids (#8562)

2024-09-23 12:32:27 -07:00

vocab_parallel_embedding.py

[Bugfix] Fix lm_head weights tying with lora for llama (#9227)

2024-10-10 21:11:56 +08:00