vllm/vllm/model_executor
Jee Jee Li fb2716d641
[Misc]Reduce BNB static variable (#9987)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-04 17:04:40 +00:00
..
guided_decoding [Frontend] Bad words sampling parameter (#9717) 2024-10-26 16:29:38 +00:00
layers [Bugfix] Fix MiniCPMV and Mllama BNB bug (#9917) 2024-11-04 03:36:41 +00:00
model_loader [Misc]Reduce BNB static variable (#9987) 2024-11-04 17:04:40 +00:00
models [Misc]Reduce BNB static variable (#9987) 2024-11-04 17:04:40 +00:00
__init__.py [Performance] Optimize e2e overheads: Reduce python allocations (#7162) 2024-08-08 21:34:28 -07:00
custom_op.py [torch.compile] rework compile control with piecewise cudagraph (#9715) 2024-10-29 23:03:49 -07:00
parameter.py [Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701) 2024-09-23 13:46:26 -04:00
pooling_metadata.py [Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734) 2024-05-11 11:30:37 -07:00
sampling_metadata.py [Spec Decode] (1/2) Remove batch expansion (#8839) 2024-10-01 16:04:42 -07:00
utils.py [Hardware] using current_platform.seed_everything (#9785) 2024-10-29 14:47:44 +00:00