 yinghui
|
18403f6bfe
|
make trtllm attn backend's init_forward_metadat non blocking (#13802)
|
2025-11-23 13:35:40 -08:00 |
|
|
yinghui
|
5a4394a342
|
align code style eagle draft&draft_extend cuda graph runner (#13533)
|
2025-11-23 01:55:16 +08:00 |
|
|
yinghui
|
38a704bccb
|
refine stdout logging codes (#13015)
|
2025-11-12 00:16:14 +08:00 |
|
|
yinghui
|
08c805a85f
|
fix(ci): workflow id in permission rate limit (#13035)
|
2025-11-11 11:06:13 +08:00 |
|
|
yinghuiandScott Lee
|
58095cb00a
|
Add timing metrics for requests (#12646)
Co-authored-by: Scott Lee <scottjlee@users.noreply.github.com>
|
2025-11-05 23:07:16 -08:00 |
|
|
yinghui
|
dc4f541823
|
fix trtllm_mla attention backend when disabling cuda graph. (#12687)
|
2025-11-05 01:35:02 -08:00 |
|
|
yinghui
|
b88fab3111
|
fix: add seed bench_serving to cache key, remove redundant function definition. (#12680)
|
2025-11-04 23:39:11 -08:00 |
|
|
yinghui
|
de0b10cf5c
|
fix: move dummy format loader check before quantization checks (#12532)
|
2025-11-02 23:41:30 -08:00 |
|
|
yinghui
|
d5b6e50fe8
|
perf: trtllm mla performance minor improvements (#12435)
|
2025-10-31 22:48:02 -07:00 |
|
|
yinghui
|
a80bcb5a68
|
Add env var to disable FA4 warmup (#12430)
|
2025-10-31 12:25:00 -07:00 |
|
|
yinghui
|
e51046beaa
|
perf: trtllm_mla attention backend spec decoding speedup w/ cuda graph (#12093)
|
2025-10-24 16:05:44 -07:00 |
|
|
yinghui
|
c23eda8589
|
Fix incorrect KV indices creation when page_size=32 in TRTLLM MLA backend (#11985)
|
2025-10-22 22:44:45 -07:00 |
|
|
yinghuiandLianmin Zheng
|
56222658ec
|
move eagle draft post process to cuda graph (#11434)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2025-10-14 22:50:53 +08:00 |
|
|
cicirori
|
a2f7218a2e
|
support using fa4 on deepseek on blackwell (#9928)
|
2025-09-16 16:16:06 -07:00 |
|
|
cicirori
|
8c5930f08a
|
Add speculator attention backend switch (#9981)
|
2025-09-07 21:44:36 -07:00 |
|
|
cicirori
|
b6c14ec0b4
|
add response_format support for completion API (#9665)
|
2025-08-26 15:01:29 -07:00 |
|