|
5fa0c6a52e
|
Allow piecewise CUDA graph with speculative decoding (#22128)
Co-authored-by: luhongyu.4869 <luhongyu.4869@bytedance.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-17 13:39:30 +08:00 |
|
|
narutolhyandluhongyu.4869
|
24763256b9
|
[Speculative Decoding] Add FA4-based Spec Support (#21080)
Co-authored-by: luhongyu.4869 <luhongyu.4869@bytedance.com>
|
2026-04-04 02:09:45 -07:00 |
|
|
narutolhy
|
8897ac58f0
|
[PP] qwen3 vl skip layer id for pp (#19135)
|
2026-04-03 10:51:53 +08:00 |
|
|
narutolhy
|
9b29131961
|
fix tp capture in vit cuda graph (#17255)
|
2026-03-27 22:38:18 +00:00 |
|
|
narutolhy
|
672b666057
|
add new ci user (#19133)
|
2026-02-23 12:48:04 -08:00 |
|
|
narutolhy
|
69cfb17b9a
|
[Fix] avoid stream sync in _compute_mrope_positions (#14956)
|
2025-12-13 18:50:57 -08:00 |
|
|
narutolhy
|
1801cd199f
|
support more model in piecewise cuda graph (#11745)
|
2025-10-24 10:31:39 +08:00 |
|
|
narutolhy
|
eb7318f1c2
|
support tokenized batch request (#11091)
|
2025-10-19 07:05:02 +00:00 |
|
|
narutolhy
|
c61b9a1d01
|
fix self.enable_kv_cache_events (#11178)
|
2025-10-03 14:09:41 -07:00 |
|
|
narutolhy
|
d17986f8c6
|
Enable optional FP32 compute for LM Head (#10729)
Thanks to MiniMax Team and Chenyang Zhao's support.
|
2025-09-29 20:45:17 -07:00 |
|
|
narutolhy
|
99757cc3e6
|
fix probs name which without temp scaling name (#9984)
|
2025-09-13 12:19:57 +08:00 |
|
|
|
839c93bd2d
|
feat: add original logprobs to response (#8375)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: luhongyu.4869 <luhongyu.4869@bytedance.com>
|
2025-08-29 11:43:57 -07:00 |
|
|
narutolhy
|
3e34e9004f
|
Fix: sync prepare_fp8_layer_for_marlin with latest vllm changes (#7648)
|
2025-06-30 21:51:01 -07:00 |
|