 maocheng23
|
2df9e8b4b3
|
[perf] DeepSeekV3: drop redundant FP32 upcasts in trtllm MoE paths (#25189)
|
2026-05-22 14:23:57 -07:00 |
|
|
maocheng23
|
6ccc5b807d
|
Optimize detokenization without HF decode kwargs (#25309)
|
2026-05-17 20:37:36 -07:00 |
|
|
maocheng23andlawrence-harmonic
|
7deed98e1b
|
[fix] /pause_generation and /continue_generation wrong for --tokenizer-worker-num > 1 (#24462)
Co-authored-by: lawrence-harmonic <185285563+lawrence-harmonic@users.noreply.github.com>
|
2026-05-07 21:32:21 -07:00 |
|
|
maocheng23andCursor
|
431ca54334
|
[fix] /pause_generation and /continue_generation wrong for --tokenizer-worker-num > 1 (#24445)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-05 16:27:58 -07:00 |
|
|
maocheng23
|
d3aa9128be
|
Change SGLANG_SIMULATE_ACC_METHOD to 'match-expected' (#23527)
|
2026-04-22 21:26:08 -07:00 |
|
|
maocheng23andClaude Opus 4.6
|
6c2a759a04
|
[fix] Fix writer lock deadlock in update_weights_from_ipc during pause_generation (#22290)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-07 18:32:56 -07:00 |
|
|
maocheng23
|
4e8829e4cd
|
Replace topk_ids with curr_topk_ids in fused_moe.py (#20302)
|
2026-03-18 21:57:05 +00:00 |
|
|
maocheng23
|
1d366f1206
|
Make bench_one_batch_server compatible for more backends (#18512)
|
2026-02-10 10:36:39 +08:00 |
|
|
maocheng23
|
b3359dc9bf
|
Update qwen3_coder_detector.py for streaming (#8371)
|
2025-08-08 14:51:03 -07:00 |
|