Divakar Verma 9dc7c6c7f3

[dbrx] refactor dbrx experts to extend FusedMoe class (#8518)

2024-09-21 15:09:39 -06:00

..

guided_decoding

Revert "[Misc][Bugfix] Disable guided decoding for mistral tokenizer" (#8593)

2024-09-19 04:14:28 +00:00

layers

[Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup MI300, minor improvement for MI250 (#8646)

2024-09-21 09:20:54 +00:00

model_loader

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

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

models

[dbrx] refactor dbrx experts to extend FusedMoe class (#8518)

2024-09-21 15:09:39 -06:00

__init__.py

[Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

custom_op.py

[torch.compile] add a flag to disable custom op (#8488)

2024-09-14 13:07:16 -07:00

parameter.py

[Misc] Update GPTQ to use vLLMParameters (#7976)

2024-09-03 17:21:44 -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

[refactor] remove triton based sampler (#8524)

2024-09-16 20:04:48 -07:00

utils.py

[CI/Build] Avoid CUDA initialization (#8534)

2024-09-18 10:38:11 +00:00