Liangsheng Yin 75ce37f401 Move sampler into CUDA graph (#1201) ...

Co-authored-by: Yineng Zhang <me@zhyncs.com>

2024-08-26 07:02:50 -07:00

..

fused_moe

Cleanup readme, llava examples, usage examples and nccl init (#1194)

2024-08-24 08:02:23 -07:00

activation.py

feat: use gelu_tanh_and_mul (#1193)

2024-08-24 01:58:16 -07:00

decode_attention.py

Cleanup readme, llava examples, usage examples and nccl init (#1194)

2024-08-24 08:02:23 -07:00

extend_attention.py

fix: temporary solution for DeepSeek V2 H100 layout conversion issue (#1060)

2024-08-13 15:48:54 +10:00

layernorm.py

fix: custom op fallback forward native when lower sm80 (#1177)

2024-08-21 14:26:35 -07:00

logits_processor.py

Move sampler into CUDA graph (#1201)

2024-08-26 07:02:50 -07:00

pooler.py

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

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

prefill_attention.py

Clean up the comments and names under python/sglang/srt/layers (#1047)

2024-08-12 05:54:37 +00:00

radix_attention.py

[Feature] Support fp8 e5m2 kv cache with flashinfer (#1204)

2024-08-25 17:38:11 -07:00

sampler.py

Move sampler into CUDA graph (#1201)

2024-08-26 07:02:50 -07:00