Update README.md
#5
by zheyishine - opened
README.md
CHANGED
|
@@ -94,6 +94,7 @@ python -m sglang.launch_server \
|
|
| 94 |
--pp-size 1 \
|
| 95 |
--dp-size 1 \
|
| 96 |
--trust-remote-code \
|
|
|
|
| 97 |
--tool-call-parser qwen25 \
|
| 98 |
--json-model-override-args '{"rope_scaling": {"rope_type": "yarn", "factor": 2.0, "rope_theta": 6000000, "partial_rotary_factor": 0.5, "original_max_position_embeddings": 131072}}' \
|
| 99 |
--dist-init-addr $MASTER_IP:2345 \
|
|
@@ -119,6 +120,7 @@ python -m sglang.launch_server \
|
|
| 119 |
--tp-size 4 \
|
| 120 |
--pp-size 1 \
|
| 121 |
--dp-size 1 \
|
|
|
|
| 122 |
--mamba-scheduler-strategy extra_buffer \
|
| 123 |
--speculative-algorithm NEXTN \
|
| 124 |
--speculative-num-steps 3 \
|
|
|
|
| 94 |
--pp-size 1 \
|
| 95 |
--dp-size 1 \
|
| 96 |
--trust-remote-code \
|
| 97 |
+
--context-length 262144 \
|
| 98 |
--tool-call-parser qwen25 \
|
| 99 |
--json-model-override-args '{"rope_scaling": {"rope_type": "yarn", "factor": 2.0, "rope_theta": 6000000, "partial_rotary_factor": 0.5, "original_max_position_embeddings": 131072}}' \
|
| 100 |
--dist-init-addr $MASTER_IP:2345 \
|
|
|
|
| 120 |
--tp-size 4 \
|
| 121 |
--pp-size 1 \
|
| 122 |
--dp-size 1 \
|
| 123 |
+
--context-length 262144 \
|
| 124 |
--mamba-scheduler-strategy extra_buffer \
|
| 125 |
--speculative-algorithm NEXTN \
|
| 126 |
--speculative-num-steps 3 \
|