44670 c530e2cfe3 [FIX] Fix a bug in initializing Yarn RoPE (#2983)

2024-02-22 01:40:05 -08:00

..

quantization

Refactor 2 awq gemm kernels into m16nXk32 (#2723)

2024-02-12 11:02:17 -08:00

triton_kernel

chore(vllm): codespell for spell checking (#2820)

2024-02-21 18:56:01 -08:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

Optimize GeGLU layer in Gemma (#2975)

2024-02-21 20:17:52 -08:00

attention.py

[ROCm] support Radeon™ 7900 series (gfx1100) without using flash-attention (#2768)

2024-02-10 23:14:37 -08:00

fused_moe.py

Add fused top-K softmax kernel for MoE (#2769)

2024-02-05 17:38:02 -08:00

layernorm.py

Revert "Refactor llama family models (#2637)" (#2851)

2024-02-13 09:24:59 -08:00

linear.py

Remove hardcoded device="cuda" to support more devices (#2503)

2024-02-01 15:46:39 -08:00

rejection_sampler.py

[Speculative decoding 1/9] Optimized rejection sampler (#2336)

2024-01-09 15:38:41 -08:00

rotary_embedding.py

[FIX] Fix a bug in initializing Yarn RoPE (#2983)

2024-02-22 01:40:05 -08:00

sampler.py

Support per-request seed (#2514)

2024-02-21 11:47:00 -08:00

vocab_parallel_embedding.py

Remove hardcoded device="cuda" to support more devices (#2503)

2024-02-01 15:46:39 -08:00