Jerry Zhang 63e845d0bb Add float8 dynamic quant to torchao_utils (#1528)

2024-09-28 12:27:54 -07:00

..

fused_moe

MoE torch compile (#1497)

2024-09-24 01:46:59 -07:00

quantization

feat: update linear deps 1/N (#1305)

2024-09-19 20:53:11 +08:00

triton_attention

Enable torch.compile for triton backend (#1422)

2024-09-14 15:38:37 -07:00

activation.py

feat: update linear deps 1/N (#1305)

2024-09-19 20:53:11 +08:00

attention_backend.py

Revert "kernel: use tensor cores for flashinfer gqa kernels" (#1511)

2024-09-24 22:50:31 -07:00

flashinfer_utils.py

Support cuda graph in the triton attention backend (#1401)

2024-09-12 00:36:55 -07:00

layernorm.py

[Bugfix] Enable SGLang on AMD GPUs via PyTorch for ROCm (#1419) (#1453)

2024-09-18 02:01:35 -07:00

linear.py

feat: update linear deps 1/N (#1305)

2024-09-19 20:53:11 +08:00

logits_processor.py

[Fix] Fix logprob and normalized_logprob (#1428)

2024-09-15 06:36:06 -07:00

pooler.py

Add e5-mistral modules [unreachable code] - step 1/3 (#983)

2024-08-08 00:04:15 -07:00

radix_attention.py

Refactor attention backend (#1381)

2024-09-11 11:44:26 -07:00

sampler.py

Fuse top_k and top_k in the sampler (#1457)

2024-09-18 04:35:35 -07:00

torchao_utils.py

Add float8 dynamic quant to torchao_utils (#1528)

2024-09-28 12:27:54 -07:00