GLM-5.1

sglang serve \
  --model-path zai-org/GLM-5.1-FP8 \
  --tp 8 \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --mem-fraction-static 0.85 \
  --host 0.0.0.0 \
  --port 30000

sglang serve \
  --model-path nvidia/GLM-5.1-NVFP4 \
  --tp 8 \
  --quantization modelopt_fp4 \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --trust-remote-code \
  --mem-fraction-static 0.80 \
  --host 0.0.0.0 \
  --port 30000

sglang serve \
  --model-path nvidia/GLM-5.1-NVFP4 \
  --tp 4 \
  --quantization modelopt_fp4 \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --trust-remote-code \
  --mem-fraction-static 0.80 \
  --host 0.0.0.0 \
  --port 30000

# SGLANG_DSA_TRITON_PREFILL=1 is optional; it enables a faster Triton prefill kernel on gfx950
SGLANG_DSA_TRITON_PREFILL=1 sglang serve \
  --model-path amd/GLM-5.1-MXFP4 \
  --tp 4 \
  --trust-remote-code \
  --kv-cache-dtype fp8_e4m3 \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --dsa-prefill-backend tilelang \
  --dsa-decode-backend tilelang \
  --chunked-prefill-size 131072 \
  --mem-fraction-static 0.85 \
  --watchdog-timeout 1200 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --disable-custom-all-reduce \
  --host 0.0.0.0 \
  --port 30000

sglang serve \
  --model-path zai-org/GLM-5.1-FP8 \
  --tp 8 \
  --trust-remote-code \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --dsa-prefill-backend tilelang \
  --dsa-decode-backend tilelang \
  --chunked-prefill-size 131072 \
  --mem-fraction-static 0.80 \
  --watchdog-timeout 1200 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --disable-custom-all-reduce \
  --host 0.0.0.0 \
  --port 30000

sglang serve \
  --model-path zai-org/GLM-5.1 \
  --tp 8 \
  --trust-remote-code \
  --dsa-prefill-backend tilelang \
  --dsa-decode-backend tilelang \
  --chunked-prefill-size 131072 \
  --mem-fraction-static 0.80 \
  --watchdog-timeout 1200 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --disable-custom-all-reduce \
  --host 0.0.0.0 \
  --port 30000

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY"
)

# Thinking mode is enabled by default, no extra parameters needed
response = client.chat.completions.create(
    model="zai-org/GLM-5.1-FP8",
    messages=[
        {"role": "user", "content": "Solve this problem step by step: What is 15% of 240?"}
    ],
    max_tokens=2048,
    stream=True
)

# Process the stream
has_thinking = False
has_answer = False
thinking_started = False

for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta

        # Print thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
            if not thinking_started:
                print("=============== Thinking =================", flush=True)
                thinking_started = True
            has_thinking = True
            print(delta.reasoning_content, end="", flush=True)

        # Print answer content
        if delta.content:
            # Close thinking section and add content header
            if has_thinking and not has_answer:
                print("\n=============== Content =================", flush=True)
                has_answer = True
            print(delta.content, end="", flush=True)

print()

=============== Thinking =================
1.  **Understand the Goal:** The user wants to find 15% of 240, and they want the solution explained step-by-step.

2.  **Identify the Core Mathematical Concept:** "Percent" means "per hundred" or "out of 100". Finding "X% of Y" translates to the mathematical operation: $(X / 100) \times Y$.

3.  **Step-by-Step Breakdown:**
    *   *Step 1: Convert the percentage to a decimal (or fraction).* 15% means 15 out of 100, which is $15/100$ or $0.15$.
    *   *Step 2: Multiply the decimal by the given number.* Multiply $0.15$ by $240$.
    *   *Step 3: Perform the calculation.*
        *   $0.15 \times 240$
        *   I can break this down further to make it easy to follow:
            *   $0.10 \times 240 = 24$ (which is 10%)
            *   $0.05 \times 240 = 12$ (which is 5%, half of 10%)
            *   $24 + 12 = 36$
        *   Alternatively, standard multiplication:
            *   $240 \times 15 = 3600$
            *   Move decimal two places left -> $36$
    *   *Step 4: State the final answer clearly.*

4.  **Draft the Response (incorporating the steps clearly):**
    *   *Introduction:* State the problem clearly.
    *   *Step 1:* Explain how to convert 15% to a decimal.
    *   *Step 2:* Explain the multiplication step.
    *   *Step 3:* Show the actual math (I'll provide the standard multiplication and the "mental math" trick as it adds value).
    *   *Conclusion:* Give the final answer.

5.  **Refine the Output (Self-Correction/Polishing during drafting):**
    *   *Drafting Step 1:* To find 15% of 240, first convert 15% into a decimal. Since percent means "per hundred," you divide 15 by 100. 15 ÷ 100 = 0.15.
    *   *Drafting Step 2:* Next, multiply this decimal by the number you are finding the percentage of (which is 240). So, calculate 0.15 × 240.
    *   *Drafting Step 3 (Standard way):* 0.15 × 240 = 36.
    *   *Adding the alternative mental math way:* It's often helpful to break it down into 10% and 5%.
        *   10% of 240 = 24 (move the decimal point one place to the left)
        *   5% is half of 10%, so half of 24 = 12
        *   Add them together: 24 + 12 = 36.
    *   *Final Answer:* 15% of 240 is 36.

6.  **Final Review against User Prompt:** Does it solve the problem? Yes. Is it step-by-step? Yes. Is it clear? Yes. (Proceed to generate output).
=============== Content =================
Here is the step-by-step solution to find 15% of 240:

**Step 1: Convert the percentage to a decimal.**
To convert a percentage to a decimal, divide it by 100 (or simply move the decimal point two places to the left).
* 15% = 15 ÷ 100 = **0.15**

**Step 2: Multiply the decimal by the number.**
Now, multiply the decimal (0.15) by the number you are finding the percentage of (240).
* 0.15 × 240 = **36**

*(Alternative mental math method for Step 2)*:
If you don't want to multiply by 0.15 directly, you can break 15% down into 10% and 5%:
* **10% of 240** = 24 (just move the decimal point one place to the left)
* **5% of 240** = 12 (5% is half of 10%, so just divide 24 by 2)
* **Add them together**: 24 + 12 = **36**

**Answer:**
15% of 240 is **36**.

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY"
)

# Disable thinking mode via chat_template_kwargs
response = client.chat.completions.create(
    model="zai-org/GLM-5.1-FP8",
    messages=[
        {"role": "user", "content": "What is 15% of 240?"}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
    max_tokens=2048,
    stream=True
)

# In Instruct mode, the model responds directly without reasoning_content
for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta
        if delta.content:
            print(delta.content, end="", flush=True)

print()

15% of 240 is 36.

Here is how to calculate it:
1. Convert the percentage to a decimal: 15% = 0.15
2. Multiply the decimal by the number: 0.15 × 240 = 36

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY"
)

# Define available tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city name"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "Temperature unit"
                    }
                },
                "required": ["location"]
            }
        }
    }
]

# Make request with streaming to see thinking process
response = client.chat.completions.create(
    model="zai-org/GLM-5.1-FP8",
    messages=[
        {"role": "user", "content": "What's the weather in Beijing?"}
    ],
    tools=tools,
    stream=True
)

# Process streaming response
thinking_started = False
has_thinking = False

for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta

        # Print thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
            if not thinking_started:
                print("=============== Thinking =================", flush=True)
                thinking_started = True
            has_thinking = True
            print(delta.reasoning_content, end="", flush=True)

        # Print tool calls
        if hasattr(delta, 'tool_calls') and delta.tool_calls:
            # Close thinking section if needed
            if has_thinking and thinking_started:
                print("\n=============== Content =================", flush=True)
                thinking_started = False

            for tool_call in delta.tool_calls:
                if tool_call.function:
                    print(f"Tool Call: {tool_call.function.name}")
                    print(f"   Arguments: {tool_call.function.arguments}")

        # Print content
        if delta.content:
            print(delta.content, end="", flush=True)

print()

=============== Thinking =================
The user wants to know the weather in Beijing. I'll call the get_weather function with "Beijing" as the location.
=============== Content =================
Tool Call: get_weather
   Arguments:
Tool Call: None
   Arguments: {
Tool Call: None
   Arguments: "location": "Be
Tool Call: None
   Arguments: ijing"
Tool Call: None
   Arguments: }

python3 -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-5.1-FP8 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 10 \
  --max-concurrency 1 \
  --request-rate inf

============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 1
Successful requests:                     10
Benchmark duration (s):                  35.78
Total input tokens:                      6101
Total input text tokens:                 6101
Total generated tokens:                  4220
Total generated tokens (retokenized):    4213
Request throughput (req/s):              0.28
Input token throughput (tok/s):          170.54
Output token throughput (tok/s):         117.96
Peak output token throughput (tok/s):    148.00
Peak concurrent requests:                2
Total token throughput (tok/s):          288.50
Concurrency:                             1.00
Accept length:                           3.48
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   3576.31
Median E2E Latency (ms):                 2935.97
P90 E2E Latency (ms):                    5908.97
P99 E2E Latency (ms):                    8588.08
---------------Time to First Token----------------
Mean TTFT (ms):                          290.88
Median TTFT (ms):                        282.34
P99 TTFT (ms):                           332.27
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          7.54
Median TPOT (ms):                        6.97
P99 TPOT (ms):                           9.04
---------------Inter-Token Latency----------------
Mean ITL (ms):                           7.80
Median ITL (ms):                         6.81
P95 ITL (ms):                            13.51
P99 ITL (ms):                            26.99
Max ITL (ms):                            29.50
==================================================

python3 -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-5.1-FP8 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 1000 \
  --max-concurrency 100 \
  --request-rate inf

============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 100
Successful requests:                     1000
Benchmark duration (s):                  411.74
Total input tokens:                      502493
Total input text tokens:                 502493
Total generated tokens:                  500251
Total generated tokens (retokenized):    499614
Request throughput (req/s):              2.43
Input token throughput (tok/s):          1220.41
Output token throughput (tok/s):         1214.97
Peak output token throughput (tok/s):    2648.00
Peak concurrent requests:                105
Total token throughput (tok/s):          2435.38
Concurrency:                             96.30
Accept length:                           3.50
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   39648.76
Median E2E Latency (ms):                 39058.12
P90 E2E Latency (ms):                    57009.82
P99 E2E Latency (ms):                    68880.33
---------------Time to First Token----------------
Mean TTFT (ms):                          20613.80
Median TTFT (ms):                        21429.21
P99 TTFT (ms):                           29543.17
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          38.73
Median TPOT (ms):                        36.52
P99 TPOT (ms):                           67.09
---------------Inter-Token Latency----------------
Mean ITL (ms):                           38.13
Median ITL (ms):                         16.57
P95 ITL (ms):                            86.01
P99 ITL (ms):                            164.88
Max ITL (ms):                            1307.02
==================================================

python3 benchmark/gsm8k/bench_sglang.py --port 30000

Accuracy: 0.955
Invalid: 0.000
Latency: 32.470 s
Output throughput: 642.044 token/s

python3 benchmark/mmlu/bench_sglang.py --port 30000

subject: abstract_algebra, #q:100, acc: 0.860
subject: anatomy, #q:135, acc: 0.874
subject: astronomy, #q:152, acc: 0.941
subject: business_ethics, #q:100, acc: 0.880
subject: clinical_knowledge, #q:265, acc: 0.932
subject: college_biology, #q:144, acc: 0.972
subject: college_chemistry, #q:100, acc: 0.640
subject: college_computer_science, #q:100, acc: 0.900
subject: college_mathematics, #q:100, acc: 0.810
subject: college_medicine, #q:173, acc: 0.873
subject: college_physics, #q:102, acc: 0.912
subject: computer_security, #q:100, acc: 0.880
subject: conceptual_physics, #q:235, acc: 0.928
subject: econometrics, #q:114, acc: 0.807
subject: electrical_engineering, #q:145, acc: 0.897
subject: elementary_mathematics, #q:378, acc: 0.937
subject: formal_logic, #q:126, acc: 0.778
subject: global_facts, #q:100, acc: 0.710
subject: high_school_biology, #q:310, acc: 0.961
subject: high_school_chemistry, #q:203, acc: 0.847
subject: high_school_computer_science, #q:100, acc: 0.960
subject: high_school_european_history, #q:165, acc: 0.891
subject: high_school_geography, #q:198, acc: 0.960
subject: high_school_government_and_politics, #q:193, acc: 0.984
subject: high_school_macroeconomics, #q:390, acc: 0.923
subject: high_school_mathematics, #q:270, acc: 0.696
subject: high_school_microeconomics, #q:238, acc: 0.962
subject: high_school_physics, #q:151, acc: 0.821
subject: high_school_psychology, #q:545, acc: 0.956
subject: high_school_statistics, #q:216, acc: 0.889
subject: high_school_us_history, #q:204, acc: 0.941
subject: high_school_world_history, #q:237, acc: 0.945
subject: human_aging, #q:223, acc: 0.857
subject: human_sexuality, #q:131, acc: 0.908
subject: international_law, #q:121, acc: 0.934
subject: jurisprudence, #q:108, acc: 0.907
subject: logical_fallacies, #q:163, acc: 0.933
subject: machine_learning, #q:112, acc: 0.830
subject: management, #q:103, acc: 0.942
subject: marketing, #q:234, acc: 0.940
subject: medical_genetics, #q:100, acc: 0.990
subject: miscellaneous, #q:783, acc: 0.959
subject: moral_disputes, #q:346, acc: 0.873
subject: moral_scenarios, #q:895, acc: 0.837
subject: nutrition, #q:306, acc: 0.922
subject: philosophy, #q:311, acc: 0.897
subject: prehistory, #q:324, acc: 0.929
subject: professional_accounting, #q:282, acc: 0.844
subject: professional_law, #q:1534, acc: 0.714
subject: professional_medicine, #q:272, acc: 0.941
subject: professional_psychology, #q:612, acc: 0.913
subject: public_relations, #q:110, acc: 0.791
subject: security_studies, #q:245, acc: 0.878
subject: sociology, #q:201, acc: 0.940
subject: us_foreign_policy, #q:100, acc: 0.920
subject: virology, #q:166, acc: 0.596
subject: world_religions, #q:171, acc: 0.936
Total latency: 165.275
Average accuracy: 0.877

python3 benchmark/gsm8k/bench_sglang.py --num-questions 200

Accuracy: 0.970
Invalid: 0.000