Skip to content

Commit b9f4795

Browse files
slarenslaren
authored
simplify bug issue template (#4623)
1 parent 753be37 commit b9f4795

File tree

1 file changed

+1
-176
lines changed

1 file changed

+1
-176
lines changed

‎.github/ISSUE_TEMPLATE/bug.md

+1-176
Original file line numberDiff line numberDiff line change
@@ -6,179 +6,4 @@ assignees: ''
66

77
---
88

9-
# Prerequisites
10-
11-
Please answer the following questions for yourself before submitting an issue.
12-
13-
- [ ] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
14-
- [ ] I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md).
15-
- [ ] I [searched using keywords relevant to my issue](https://docs.github.com/en/issues/tracking-your-work-with-issues/filtering-and-searching-issues-and-pull-requests) to make sure that I am creating a new issue that is not already open (or closed).
16-
- [ ] I reviewed the [Discussions](https://github.com/ggerganov/llama.cpp/discussions), and have a new bug or useful enhancement to share.
17-
18-
# Expected Behavior
19-
20-
Please provide a detailed written description of what you were trying to do, and what you expected `llama.cpp` to do.
21-
22-
# Current Behavior
23-
24-
Please provide a detailed written description of what `llama.cpp` did, instead.
25-
26-
# Environment and Context
27-
28-
Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.
29-
30-
* Physical (or virtual) hardware you are using, e.g. for Linux:
31-
32-
`$ lscpu`
33-
34-
* Operating System, e.g. for Linux:
35-
36-
`$ uname -a`
37-
38-
* SDK version, e.g. for Linux:
39-
40-
```
41-
$ python3 --version
42-
$ make --version
43-
$ g++ --version
44-
```
45-
46-
# Failure Information (for bugs)
47-
48-
Please help provide information about the failure / bug.
49-
50-
# Steps to Reproduce
51-
52-
Please provide detailed steps for reproducing the issue. We are not sitting in front of your screen, so the more detail the better.
53-
54-
1. step 1
55-
2. step 2
56-
3. step 3
57-
4. etc.
58-
59-
# Failure Logs
60-
61-
Please include any relevant log snippets or files. If it works under one configuration but not under another, please provide logs for both configurations and their corresponding outputs so it is easy to see where behavior changes.
62-
63-
Also, please try to **avoid using screenshots** if at all possible. Instead, copy/paste the console output and use [Github's markdown](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax) to cleanly format your logs for easy readability.
64-
65-
Example environment info:
66-
```
67-
llama.cpp$ git log | head -1
68-
commit 2af23d30434a677c6416812eea52ccc0af65119c
69-
70-
llama.cpp$ lscpu | egrep "AMD|Flags"
71-
Vendor ID: AuthenticAMD
72-
Model name: AMD Ryzen Threadripper 1950X 16-Core Processor
73-
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid amd_dcm aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb hw_pstate ssbd ibpb vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt sha_ni xsaveopt xsavec xgetbv1 xsaves clzero irperf xsaveerptr arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca sme sev
74-
Virtualization: AMD-V
75-
76-
llama.cpp$ python3 --version
77-
Python 3.10.9
78-
79-
llama.cpp$ pip list | egrep "torch|numpy|sentencepiece"
80-
numpy 1.24.2
81-
numpydoc 1.5.0
82-
sentencepiece 0.1.97
83-
torch 1.13.1
84-
torchvision 0.14.1
85-
86-
llama.cpp$ make --version | head -1
87-
GNU Make 4.3
88-
89-
$ md5sum ./models/65B/ggml-model-q4_0.bin
90-
dbdd682cce80e2d6e93cefc7449df487 ./models/65B/ggml-model-q4_0.bin
91-
```
92-
93-
Example run with the Linux command [perf](https://www.brendangregg.com/perf.html)
94-
```
95-
llama.cpp$ perf stat ./main -m ./models/65B/ggml-model-q4_0.bin -t 16 -n 1024 -p "Please close your issue when it has been answered."
96-
main: seed = 1679149377
97-
llama_model_load: loading model from './models/65B/ggml-model-q4_0.bin' - please wait ...
98-
llama_model_load: n_vocab = 32000
99-
llama_model_load: n_ctx = 512
100-
llama_model_load: n_embd = 8192
101-
llama_model_load: n_mult = 256
102-
llama_model_load: n_head = 64
103-
llama_model_load: n_layer = 80
104-
llama_model_load: n_rot = 128
105-
llama_model_load: f16 = 2
106-
llama_model_load: n_ff = 22016
107-
llama_model_load: n_parts = 8
108-
llama_model_load: ggml ctx size = 41477.73 MB
109-
llama_model_load: memory_size = 2560.00 MB, n_mem = 40960
110-
llama_model_load: loading model part 1/8 from './models/65B/ggml-model-q4_0.bin'
111-
llama_model_load: .......................................................................................... done
112-
llama_model_load: model size = 4869.09 MB / num tensors = 723
113-
llama_model_load: loading model part 2/8 from './models/65B/ggml-model-q4_0.bin.1'
114-
llama_model_load: .......................................................................................... done
115-
llama_model_load: model size = 4869.09 MB / num tensors = 723
116-
llama_model_load: loading model part 3/8 from './models/65B/ggml-model-q4_0.bin.2'
117-
llama_model_load: .......................................................................................... done
118-
llama_model_load: model size = 4869.09 MB / num tensors = 723
119-
llama_model_load: loading model part 4/8 from './models/65B/ggml-model-q4_0.bin.3'
120-
llama_model_load: .......................................................................................... done
121-
llama_model_load: model size = 4869.09 MB / num tensors = 723
122-
llama_model_load: loading model part 5/8 from './models/65B/ggml-model-q4_0.bin.4'
123-
llama_model_load: .......................................................................................... done
124-
llama_model_load: model size = 4869.09 MB / num tensors = 723
125-
llama_model_load: loading model part 6/8 from './models/65B/ggml-model-q4_0.bin.5'
126-
llama_model_load: .......................................................................................... done
127-
llama_model_load: model size = 4869.09 MB / num tensors = 723
128-
llama_model_load: loading model part 7/8 from './models/65B/ggml-model-q4_0.bin.6'
129-
llama_model_load: .......................................................................................... done
130-
llama_model_load: model size = 4869.09 MB / num tensors = 723
131-
llama_model_load: loading model part 8/8 from './models/65B/ggml-model-q4_0.bin.7'
132-
llama_model_load: .......................................................................................... done
133-
llama_model_load: model size = 4869.09 MB / num tensors = 723
134-
135-
system_info: n_threads = 16 / 32 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 |
136-
137-
main: prompt: 'Please close your issue when it has been answered.'
138-
main: number of tokens in prompt = 11
139-
1 -> ''
140-
12148 -> 'Please'
141-
3802 -> ' close'
142-
596 -> ' your'
143-
2228 -> ' issue'
144-
746 -> ' when'
145-
372 -> ' it'
146-
756 -> ' has'
147-
1063 -> ' been'
148-
7699 -> ' answered'
149-
29889 -> '.'
150-
151-
sampling parameters: temp = 0.800000, top_k = 40, top_p = 0.950000, repeat_last_n = 64, repeat_penalty = 1.300000
152-
153-
154-
Please close your issue when it has been answered.
155-
@duncan-donut: I'm trying to figure out what kind of "support" you need for this script and why, exactly? Is there a question about how the code works that hasn't already been addressed in one or more comments below this ticket, or are we talking something else entirely like some sorta bugfixing job because your server setup is different from mine??
156-
I can understand if your site needs to be running smoothly and you need help with a fix of sorts but there should really be nothing wrong here that the code itself could not handle. And given that I'm getting reports about how it works perfectly well on some other servers, what exactly are we talking? A detailed report will do wonders in helping us get this resolved for ya quickly so please take your time and describe the issue(s) you see as clearly & concisely as possible!!
157-
@duncan-donut: I'm not sure if you have access to cPanel but you could try these instructions. It is worth a shot! Let me know how it goes (or what error message, exactly!) when/if ya give that code a go? [end of text]
158-
159-
160-
main: mem per token = 71159620 bytes
161-
main: load time = 19309.95 ms
162-
main: sample time = 168.62 ms
163-
main: predict time = 223895.61 ms / 888.47 ms per token
164-
main: total time = 246406.42 ms
165-
166-
Performance counter stats for './main -m ./models/65B/ggml-model-q4_0.bin -t 16 -n 1024 -p Please close your issue when it has been answered.':
167-
168-
3636882.89 msec task-clock # 14.677 CPUs utilized
169-
13509 context-switches # 3.714 /sec
170-
2436 cpu-migrations # 0.670 /sec
171-
10476679 page-faults # 2.881 K/sec
172-
13133115082869 cycles # 3.611 GHz (16.77%)
173-
29314462753 stalled-cycles-frontend # 0.22% frontend cycles idle (16.76%)
174-
10294402631459 stalled-cycles-backend # 78.39% backend cycles idle (16.74%)
175-
23479217109614 instructions # 1.79 insn per cycle
176-
# 0.44 stalled cycles per insn (16.76%)
177-
2353072268027 branches # 647.002 M/sec (16.77%)
178-
1998682780 branch-misses # 0.08% of all branches (16.76%)
179-
180-
247.802177522 seconds time elapsed
181-
182-
3618.573072000 seconds user
183-
18.491698000 seconds sys
184-
```
9+
Please include information about your system, the steps to reproduce the bug, and the version of llama.cpp that you are using. If possible, please provide a minimal code example that reproduces the bug.

0 commit comments

Comments
 (0)