- 05 Dec, 2025 2 commits
- 04 Dec, 2025 4 commits
- 03 Dec, 2025 3 commits
- 02 Dec, 2025 2 commits
- 30 Nov, 2025 1 commit
-
-
王敏 authored
-
- 26 Nov, 2025 2 commits
- 25 Nov, 2025 1 commit
-
-
zhuwenwen authored
-
- 24 Nov, 2025 2 commits
- 21 Nov, 2025 1 commit
-
-
zhuwenwen authored
-
- 20 Nov, 2025 3 commits
- 18 Nov, 2025 1 commit
-
-
王敏 authored
-
- 17 Nov, 2025 2 commits
- 14 Nov, 2025 2 commits
- 13 Nov, 2025 8 commits
-
-
zhuwenwen authored
set default_max_num_batched_tokens = 10240 update qwen3_moe of layernorm off lightop of moe_fused_gate
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
add VLLM_USE_PD_SPLIT to split prefill and decode replace triton_ of rms and act_and_mul
-
zhuwenwen authored
-
zhuwenwen authored
add deps of pd-pp
-
王敏 authored
-
zhuwenwen authored
-
- 31 Oct, 2025 4 commits
- 30 Oct, 2025 1 commit
-
-
zhuwenwen authored
-
- 29 Oct, 2025 1 commit
-
-
zhuwenwen authored
# 第一个ip为D的第一个节点,第二个ip为D的第二个节点,配置:export IP_CONFIG_FILE=/data/xiabo/w4a8_1/ip_config.txt 192.168.1.1 192.168.1.100 192.168.1.2 192.168.1.101 192.168.1.3 192.168.1.102 10.16.1.75 10.16.1.76
-