SILONG ZENG
78af0c30a3
[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #12 ) ( #6177 )
...
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| `vllm_ascend/ops/triton/activation/swiglu_quant.py` |
| `vllm_ascend/ops/triton/batch_invariant/matmul.py` |
| `vllm_ascend/ops/triton/batch_invariant/mean.py` |
| `vllm_ascend/ops/triton/batch_invariant/rmsnorm.py` |
| `vllm_ascend/ops/triton/fla/chunk.py` |
| `vllm_ascend/ops/triton/fla/chunk_delta_h.py` |
| `vllm_ascend/ops/triton/fla/chunk_o.py` |
| `vllm_ascend/ops/triton/fla/chunk_scaled_dot_kkt.py` |
| `vllm_ascend/ops/triton/fla/cumsum.py` |
| `vllm_ascend/ops/triton/fla/fused_qkvzba_split_reshape.py` |
| `vllm_ascend/ops/triton/fla/l2norm.py` |
| `vllm_ascend/ops/triton/fla/layernorm_guard.py` |
| `vllm_ascend/ops/triton/fla/sigmoid_gating.py` |
| `vllm_ascend/ops/triton/fla/solve_tril.py` |
| `vllm_ascend/ops/triton/fla/utils.py` |
| `vllm_ascend/ops/triton/fla/wy_fast.py` |
| `vllm_ascend/ops/triton/fused_gdn_gating.py` |
| `vllm_ascend/ops/triton/layernorm_gated.py` |
| `vllm_ascend/ops/triton/linearnorm/split_qkv_rmsnorm_rope.py` |
| `vllm_ascend/ops/triton/mamba/causal_conv1d.py` |
| `vllm_ascend/ops/triton/reject_sample.py` |
| `vllm_ascend/ops/triton/rope.py` |
| `vllm_ascend/ops/triton/spec_decode/utils.py` |
| `vllm_ascend/ops/triton/triton_utils.py` |
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.0
- vLLM main:
d68209402d2609716663@qq.com >
2026-01-23 14:59:19 +08:00
Aoxuan Chen
8763953f56
[Feature] add the magicmtp speculative decoding acceleration algorithm ( #5542 )
...
### What this PR does / why we need it?
1. MagicMTP (paper: "Block Verification Accelerates Speculative
Decoding") was introduced to consider the influence among multiple draft
tokens, improving the acceptance rate without compromising accuracy.
2. Added Triton and PyTorch implementations, and added E2E test cases.
### Does this PR introduce _any_ user-facing change?
MagicMTP will automatically take effect when the parameter
"num_speculative_tokens" >= 3.
- vLLM version: v0.13.0
- vLLM main:
7157596103cax1165@163.com >
2026-01-08 09:15:55 +08:00
daniel
8ffe3f5d78
feat: implement high-performance Triton kernels for rejection sampling: optimization for rejection_random_sample_kernel ( #5259 )
...
### What this PR does / why we need it?
This PR introduces optimized Triton implementations for the
rejection_random_sample_kernel delivering superior performance compared
to the existing Triton implementations. The new Triton kernels maintain
full functional accuracy while delivering significant performance
improvements across various batch sizes and MTP configurations.
### Does this PR introduce _any_ user-facing change?
Yes, this PR modifies rejection_sampler.py to use optimized Triton
kernels:
rejection_random_sample_kernel is modified and optimized
### How was this patch tested?
performance benchmark results:
<html xmlns:v="urn:schemas-microsoft-com:vml"
xmlns:o="urn:schemas-microsoft-com:office:office"
xmlns:x="urn:schemas-microsoft-com:office:excel"
xmlns="http://www.w3.org/TR/REC-html40 ">
<head>
<meta name=Generator content="Microsoft Excel">
<!--[if !mso]>
</head>
<body>
<!--StartFragment-->
Batch Size | MTP | origin implementation(us) | optimized version(us)
-- | -- | -- | --
1 | 1 | 2.934 | 3.64
8 | 1 | 4.467 | 4
32 | 1 | 6.98 | 4.54
64 | 1 | 11.087 | 6.42
128 | 1 | 13.414 | 7.84
256 | 1 | 19.66 | 8.487
512 | 1 | 39.908 | 11.62
1024 | 1 | 81.781 | 18.16
2048 | 1 | 137.923 | 32.934
1 | 2 | 3.4 | 4.02
8 | 2 | 3.74 | 4.24
32 | 2 | 6.373 | 7.394
64 | 2 | 9.747 | 6.46
128 | 2 | 12.98 | 7.76
256 | 2 | 20.834 | 9.787
512 | 2 | 39.314 | 13.56
1024 | 2 | 83.135 | 22.387
2048 | 2 | 157.563 | 40.607
<!--EndFragment-->
</body>
</html>
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19cxxltju324@gmail.com >
2026-01-05 16:03:02 +08:00
whx
28b7614322
[Refactor][Triton] Move reject sample triton kernels into ops/triton ( #5324 )
...
### What this PR does / why we need it?
This PR moves reject sample related triton kernels into `ops/triton`.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed with existing test.
- vLLM version: release/v0.13.0
- vLLM main:
5fbfa8d9ef2952154980@qq.com >
2025-12-29 16:15:41 +08:00
