Loop :(
Config:
"A:/0_llama_server/llama-server.exe" -m "a:\0_LM_Studio\Jackrong\Qwopus3.6-27B-Coder-Compat-MTP-GGUF\Qwopus3.6-27B-Coder-Compat-MTP-Q5_K_M.gguf" --port 8080 --alias smart -ngl 999 --threads 22 --flash-attn on --host 0.0.0.0 --no-mmap --parallel 1 --fit off -mg 1 --no-mmproj-offload --cache-ram 65536 --ctx-size 202750 --jinja --spec-type draft-mtp,ngram-mod --spec-draft-n-max 2 --spec-ngram-mod-n-match 24 --spec-ngram-mod-n-min 48 --spec-ngram-mod-n-max 64 --reasoning off --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 --repeat_penalty 1.0 --presence_penalty 1.0 --chat-template-kwargs "{"preserve_thinking":false}" --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768 --mmproj a:\0_LM_Studio\Jackrong\Qwopus3.6-27B-Coder-Compat-MTP-GGUF\mmproj-F32.gguf
hermes:
The switchTab function is missing the workersView display toggle. Let me fix it:
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┊ 💻 preparing terminal…
╭─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
The switchTab function is missing the workersView display toggle. Let me fix it:
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┊ 💻 preparing terminal…
╭─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
The switchTab function is missing the workersView display toggle. Let me fix it:
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┊ 💻 preparing terminal…
╭─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
The switchTab function is missing the workersView display toggle. Let me fix it:
[0m[34m4.34.226.271[0m [32mI [0mslot create_check: id 0 | task 283 | created context checkpoint 11 of 32 (pos_min = 107457, pos_max = 107457, n_tokens = 107458, size = 571.434 MiB)
[34m4.35.958.083[0m [32mI [0mslot print_timing: id 0 | task 283 | prompt processing, n_tokens = 582, progress = 1.00, t = 3.10 s / 187.48 tokens per second
[34m4.36.104.216[0m [32mI [0mbegin: ngram_mod occupancy = 72665/4194304 (0.02)
[34m4.38.561.683[0m [32mI [0mslot print_timing: id 0 | task 283 | prompt eval time = 3251.18 ms / 586 tokens ( 5.55 ms per token, 180.24 tokens per second)
[34m4.38.561.688[0m [32mI [0mslot print_timing: id 0 | task 283 | eval time = 2456.29 ms / 136 tokens ( 18.06 ms per token, 55.37 tokens per second)
[34m4.38.561.689[0m [32mI [0mslot print_timing: id 0 | task 283 | total time = 5707.47 ms / 722 tokens
[34m4.38.561.691[0m [32mI [0mslot print_timing: id 0 | task 283 | graphs reused = 25
[34m4.38.561.734[0m [32mI [0mslot print_timing: id 0 | task 283 | draft acceptance = 0.88889 ( 128 accepted / 144 generated), mean acceptance length = 13.80, acceptance rate per position = (1.000, 1.000, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100, 0.100)
[34m4.38.561.804[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 3 29 5, #gen drafts = 5, #acc drafts = 5, #gen tokens = 320, #acc tokens = 167, #mean acc len = 34.40, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200, 0.200), dur(b,g,a) = 18.402, 0.140, 0.014 ms
[34m4.38.561.812[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 3 24 24, #gen drafts = 24, #acc drafts = 24, #gen tokens = 48, #acc tokens = 48, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.005, 291.353, 0.024 ms
[34m4.38.564.640[0m [32mI [0mslot release: id 0 | task 283 | stop processing: n_tokens = 108015, truncated = 0
[34m4.38.564.850[0m [32mI [0msrv update_slots: all slots are idle
[34m4.40.249.286[0m [32mI [0msrv operator(): Chat format: peg-native
[34m4.40.254.170[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m4.40.255.646[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m4.40.255.652[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m4.40.255.861[0m [32mI [0mslot launch_slot_: id 0 | task 299 | processing task, is_child = 0
[34m4.40.256.052[0m [32mI [0mslot operator(): id 0 | task 299 | Checking checkpoint with [107457, 107457] against 107873...
[34m4.40.357.772[0m [35mW slot operator(): id 0 | task 299 | restored context checkpoint (pos_min = 107457, pos_max = 107457, n_tokens = 107458, n_past = 107458, size = 571.434 MiB)
[0m[34m4.43.038.795[0m [32mI [0mslot create_check: id 0 | task 299 | created context checkpoint 12 of 32 (pos_min = 108009, pos_max = 108009, n_tokens = 108010, size = 573.600 MiB)
[34m4.43.382.267[0m [32mI [0mbegin: ngram_mod occupancy = 72695/4194304 (0.02)
[34m4.45.102.888[0m [32mI [0mslot print_timing: id 0 | task 299 | prompt eval time = 3127.18 ms / 586 tokens ( 5.34 ms per token, 187.39 tokens per second)
[34m4.45.102.894[0m [32mI [0mslot print_timing: id 0 | task 299 | eval time = 1719.45 ms / 136 tokens ( 12.64 ms per token, 79.09 tokens per second)
[34m4.45.102.896[0m [32mI [0mslot print_timing: id 0 | task 299 | total time = 4846.63 ms / 722 tokens
[34m4.45.102.897[0m [32mI [0mslot print_timing: id 0 | task 299 | graphs reused = 27
[34m4.45.102.949[0m [32mI [0mslot print_timing: id 0 | task 299 | draft acceptance = 0.70312 ( 135 accepted / 192 generated), mean acceptance length = 46.00, acceptance rate per position = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667)
[34m4.45.103.060[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 4 32 8, #gen drafts = 8, #acc drafts = 8, #gen tokens = 512, #acc tokens = 302, #mean acc len = 38.75, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.875, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.625, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375, 0.375), dur(b,g,a) = 24.474, 0.194, 0.018 ms
[34m4.45.103.068[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 4 24 24, #gen drafts = 24, #acc drafts = 24, #gen tokens = 48, #acc tokens = 48, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.007, 291.353, 0.024 ms
[34m4.45.105.819[0m [32mI [0mslot release: id 0 | task 299 | stop processing: n_tokens = 108182, truncated = 0
[34m4.45.106.065[0m [32mI [0msrv update_slots: all slots are idle
[34m4.46.587.505[0m [32mI [0msrv operator(): Chat format: peg-native
[34m4.46.592.357[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m4.46.593.886[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m4.46.593.891[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m4.46.594.121[0m [32mI [0mslot launch_slot_: id 0 | task 308 | processing task, is_child = 0
[34m4.46.594.303[0m [32mI [0mslot operator(): id 0 | task 308 | Checking checkpoint with [108009, 108009] against 108040...
[34m4.46.697.348[0m [35mW slot operator(): id 0 | task 308 | restored context checkpoint (pos_min = 108009, pos_max = 108009, n_tokens = 108010, n_past = 108010, size = 573.600 MiB)
[0m[34m4.47.900.568[0m [32mI [0mslot create_check: id 0 | task 308 | created context checkpoint 13 of 32 (pos_min = 108176, pos_max = 108176, n_tokens = 108177, size = 574.256 MiB)
[34m4.48.244.906[0m [32mI [0mbegin: ngram_mod occupancy = 72695/4194304 (0.02)
[34m4.50.556.149[0m [32mI [0mslot print_timing: id 0 | task 308 | prompt eval time = 1651.75 ms / 201 tokens ( 8.22 ms per token, 121.69 tokens per second)
[34m4.50.556.157[0m [32mI [0mslot print_timing: id 0 | task 308 | eval time = 2309.87 ms / 67 tokens ( 34.48 ms per token, 29.01 tokens per second)
[34m4.50.556.158[0m [32mI [0mslot print_timing: id 0 | task 308 | total time = 3961.61 ms / 268 tokens
[34m4.50.556.159[0m [32mI [0mslot print_timing: id 0 | task 308 | graphs reused = 31
[34m4.50.556.201[0m [32mI [0mslot print_timing: id 0 | task 308 | draft acceptance = 0.43571 ( 61 accepted / 140 generated), mean acceptance length = 8.62, acceptance rate per position = (1.000, 1.000, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.250, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000)
[34m4.50.556.273[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 5 40 10, #gen drafts = 10, #acc drafts = 10, #gen tokens = 640, #acc tokens = 351, #mean acc len = 36.10, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.900, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.800, 0.700, 0.700, 0.700, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.600, 0.500, 0.500, 0.500, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.400, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300, 0.300), dur(b,g,a) = 30.521, 0.245, 0.019 ms
[34m4.50.556.281[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 5 30 30, #gen drafts = 30, #acc drafts = 30, #gen tokens = 60, #acc tokens = 60, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.009, 364.039, 0.031 ms
[34m4.50.559.123[0m [32mI [0mslot release: id 0 | task 308 | stop processing: n_tokens = 108280, truncated = 0
[34m4.50.559.349[0m [32mI [0msrv update_slots: all slots are idle
[34m4.52.363.878[0m [32mI [0msrv operator(): Chat format: peg-native
[34m4.52.368.702[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m4.52.370.248[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m4.52.370.253[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m4.52.370.456[0m [32mI [0mslot launch_slot_: id 0 | task 322 | processing task, is_child = 0
[34m4.52.370.640[0m [32mI [0mslot operator(): id 0 | task 322 | Checking checkpoint with [108176, 108176] against 108207...
[34m4.52.474.521[0m [35mW slot operator(): id 0 | task 322 | restored context checkpoint (pos_min = 108176, pos_max = 108176, n_tokens = 108177, n_past = 108177, size = 574.256 MiB)
[0m[34m4.53.370.800[0m [32mI [0mslot create_check: id 0 | task 322 | created context checkpoint 14 of 32 (pos_min = 108274, pos_max = 108274, n_tokens = 108275, size = 574.641 MiB)
[34m4.54.179.946[0m [32mI [0mbegin: ngram_mod occupancy = 72715/4194304 (0.02)
[34m4.56.109.054[0m [32mI [0mslot print_timing: id 0 | task 322 | prompt eval time = 1810.40 ms / 259 tokens ( 6.99 ms per token, 143.06 tokens per second)
[34m4.56.109.061[0m [32mI [0mslot print_timing: id 0 | task 322 | eval time = 1927.79 ms / 48 tokens ( 40.16 ms per token, 24.90 tokens per second)
[34m4.56.109.062[0m [32mI [0mslot print_timing: id 0 | task 322 | total time = 3738.19 ms / 307 tokens
[34m4.56.109.063[0m [32mI [0mslot print_timing: id 0 | task 322 | graphs reused = 38
[34m4.56.109.103[0m [32mI [0mslot print_timing: id 0 | task 322 | draft acceptance = 0.51250 ( 41 accepted / 80 generated), mean acceptance length = 5.56, acceptance rate per position = (1.000, 1.000, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.111, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000)
[34m4.56.109.174[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 6 49 11, #gen drafts = 11, #acc drafts = 11, #gen tokens = 704, #acc tokens = 376, #mean acc len = 35.18, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.909, 0.818, 0.818, 0.818, 0.818, 0.818, 0.818, 0.818, 0.818, 0.818, 0.818, 0.818, 0.727, 0.727, 0.727, 0.636, 0.636, 0.636, 0.636, 0.545, 0.545, 0.545, 0.455, 0.455, 0.455, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.364, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273, 0.273), dur(b,g,a) = 36.543, 0.276, 0.020 ms
[34m4.56.109.183[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 6 38 38, #gen drafts = 38, #acc drafts = 38, #gen tokens = 76, #acc tokens = 76, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.010, 459.781, 0.039 ms
[34m4.56.112.060[0m [32mI [0mslot release: id 0 | task 322 | stop processing: n_tokens = 108486, truncated = 0
[34m4.56.112.293[0m [32mI [0msrv update_slots: all slots are idle
[34m4.57.744.350[0m [32mI [0msrv operator(): Chat format: peg-native
[34m4.57.749.302[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.996 (> 0.100 thold), f_keep = 1.000
[34m4.57.750.915[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m4.57.750.920[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m4.57.751.131[0m [32mI [0mslot launch_slot_: id 0 | task 336 | processing task, is_child = 0
[34m4.57.751.312[0m [32mI [0mslot operator(): id 0 | task 336 | Checking checkpoint with [108274, 108274] against 108432...
[34m4.57.853.008[0m [35mW slot operator(): id 0 | task 336 | restored context checkpoint (pos_min = 108274, pos_max = 108274, n_tokens = 108275, n_past = 108275, size = 574.641 MiB)
[0m[34m4.59.202.288[0m [32mI [0mslot create_check: id 0 | task 336 | created context checkpoint 15 of 32 (pos_min = 108480, pos_max = 108480, n_tokens = 108481, size = 575.449 MiB)
[34m5.00.939.625[0m [32mI [0mslot print_timing: id 0 | task 336 | prompt processing, n_tokens = 631, progress = 1.00, t = 3.19 s / 197.90 tokens per second
[34m5.01.081.758[0m [32mI [0mbegin: ngram_mod occupancy = 72734/4194304 (0.02)
[34m5.02.866.818[0m [32mI [0mslot print_timing: id 0 | task 336 | prompt eval time = 3331.58 ms / 635 tokens ( 5.25 ms per token, 190.60 tokens per second)
[34m5.02.866.826[0m [32mI [0mslot print_timing: id 0 | task 336 | eval time = 1783.71 ms / 136 tokens ( 13.12 ms per token, 76.25 tokens per second)
[34m5.02.866.827[0m [32mI [0mslot print_timing: id 0 | task 336 | total time = 5115.30 ms / 771 tokens
[34m5.02.866.828[0m [32mI [0mslot print_timing: id 0 | task 336 | graphs reused = 39
[34m5.02.866.874[0m [32mI [0mslot print_timing: id 0 | task 336 | draft acceptance = 0.70312 ( 135 accepted / 192 generated), mean acceptance length = 46.00, acceptance rate per position = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667)
[34m5.02.866.947[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 7 52 14, #gen drafts = 14, #acc drafts = 14, #gen tokens = 896, #acc tokens = 511, #mean acc len = 37.50, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.929, 0.786, 0.786, 0.786, 0.786, 0.786, 0.786, 0.786, 0.786, 0.786, 0.786, 0.786, 0.714, 0.714, 0.714, 0.643, 0.643, 0.643, 0.643, 0.571, 0.571, 0.571, 0.500, 0.500, 0.500, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.429, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357, 0.357), dur(b,g,a) = 42.647, 0.329, 0.023 ms
[34m5.02.866.967[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 7 38 38, #gen drafts = 38, #acc drafts = 38, #gen tokens = 76, #acc tokens = 76, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.012, 459.781, 0.039 ms
[34m5.02.869.777[0m [32mI [0mslot release: id 0 | task 336 | stop processing: n_tokens = 109048, truncated = 0
[34m5.02.869.986[0m [32mI [0msrv update_slots: all slots are idle
[34m5.04.440.268[0m [32mI [0msrv operator(): Chat format: peg-native
[34m5.04.445.090[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m5.04.446.706[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m5.04.446.711[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m5.04.446.912[0m [32mI [0mslot launch_slot_: id 0 | task 345 | processing task, is_child = 0
[34m5.04.447.105[0m [32mI [0mslot operator(): id 0 | task 345 | Checking checkpoint with [108480, 108480] against 108906...
[34m5.04.549.541[0m [35mW slot operator(): id 0 | task 345 | restored context checkpoint (pos_min = 108480, pos_max = 108480, n_tokens = 108481, n_past = 108481, size = 575.449 MiB)
[0m[34m5.07.153.654[0m [32mI [0mslot create_check: id 0 | task 345 | created context checkpoint 16 of 32 (pos_min = 109042, pos_max = 109042, n_tokens = 109043, size = 577.655 MiB)
[34m5.07.494.006[0m [32mI [0mbegin: ngram_mod occupancy = 72736/4194304 (0.02)
[34m5.09.284.233[0m [32mI [0mslot print_timing: id 0 | task 345 | prompt eval time = 3047.93 ms / 596 tokens ( 5.11 ms per token, 195.54 tokens per second)
[34m5.09.284.239[0m [32mI [0mslot print_timing: id 0 | task 345 | eval time = 1789.00 ms / 136 tokens ( 13.15 ms per token, 76.02 tokens per second)
[34m5.09.284.240[0m [32mI [0mslot print_timing: id 0 | task 345 | total time = 4836.93 ms / 732 tokens
[34m5.09.284.241[0m [32mI [0mslot print_timing: id 0 | task 345 | graphs reused = 41
[34m5.09.284.287[0m [32mI [0mslot print_timing: id 0 | task 345 | draft acceptance = 0.70312 ( 135 accepted / 192 generated), mean acceptance length = 46.00, acceptance rate per position = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667)
[34m5.09.284.361[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 8 55 17, #gen drafts = 17, #acc drafts = 17, #gen tokens = 1088, #acc tokens = 646, #mean acc len = 39.00, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.941, 0.765, 0.765, 0.765, 0.765, 0.765, 0.765, 0.765, 0.765, 0.765, 0.765, 0.765, 0.706, 0.706, 0.706, 0.647, 0.647, 0.647, 0.647, 0.588, 0.588, 0.588, 0.529, 0.529, 0.529, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.471, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412, 0.412), dur(b,g,a) = 48.811, 0.380, 0.027 ms
[34m5.09.284.369[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 8 38 38, #gen drafts = 38, #acc drafts = 38, #gen tokens = 76, #acc tokens = 76, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.014, 459.781, 0.039 ms
[34m5.09.287.181[0m [32mI [0mslot release: id 0 | task 345 | stop processing: n_tokens = 109215, truncated = 0
[34m5.09.287.430[0m [32mI [0msrv update_slots: all slots are idle
[34m5.10.871.439[0m [32mI [0msrv operator(): Chat format: peg-native
[34m5.10.876.506[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m5.10.877.972[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m5.10.877.977[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m5.10.878.191[0m [32mI [0mslot launch_slot_: id 0 | task 354 | processing task, is_child = 0
[34m5.10.878.374[0m [32mI [0mslot operator(): id 0 | task 354 | Checking checkpoint with [109042, 109042] against 109073...
[34m5.10.983.113[0m [35mW slot operator(): id 0 | task 354 | restored context checkpoint (pos_min = 109042, pos_max = 109042, n_tokens = 109043, n_past = 109043, size = 577.655 MiB)
[0m[34m5.12.255.508[0m [32mI [0mslot create_check: id 0 | task 354 | created context checkpoint 17 of 32 (pos_min = 109209, pos_max = 109209, n_tokens = 109210, size = 578.311 MiB)
[34m5.12.602.996[0m [32mI [0mbegin: ngram_mod occupancy = 72736/4194304 (0.02)
[34m5.14.393.818[0m [32mI [0mslot print_timing: id 0 | task 354 | prompt eval time = 1725.76 ms / 201 tokens ( 8.59 ms per token, 116.47 tokens per second)
[34m5.14.393.825[0m [32mI [0mslot print_timing: id 0 | task 354 | eval time = 1789.50 ms / 136 tokens ( 13.16 ms per token, 76.00 tokens per second)
[34m5.14.393.827[0m [32mI [0mslot print_timing: id 0 | task 354 | total time = 3515.25 ms / 337 tokens
[34m5.14.393.828[0m [32mI [0mslot print_timing: id 0 | task 354 | graphs reused = 42
[34m5.14.393.873[0m [32mI [0mslot print_timing: id 0 | task 354 | draft acceptance = 0.70312 ( 135 accepted / 192 generated), mean acceptance length = 46.00, acceptance rate per position = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667, 0.667)
[34m5.14.393.952[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 9 58 20, #gen drafts = 20, #acc drafts = 20, #gen tokens = 1280, #acc tokens = 781, #mean acc len = 40.05, #acc rate/pos = (1.000, 1.000, 1.000, 1.000, 1.000, 1.000, 0.950, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.750, 0.700, 0.700, 0.700, 0.650, 0.650, 0.650, 0.650, 0.600, 0.600, 0.600, 0.550, 0.550, 0.550, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450, 0.450), dur(b,g,a) = 55.071, 0.433, 0.031 ms
[34m5.14.393.964[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 9 38 38, #gen drafts = 38, #acc drafts = 38, #gen tokens = 76, #acc tokens = 76, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.016, 459.781, 0.039 ms
[34m5.14.396.732[0m [32mI [0mslot release: id 0 | task 354 | stop processing: n_tokens = 109382, truncated = 0
[34m5.14.396.937[0m [32mI [0msrv update_slots: all slots are idle
[34m5.16.337.586[0m [32mI [0msrv operator(): Chat format: peg-native
[34m5.16.342.511[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m5.16.343.963[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m5.16.343.967[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m5.16.344.172[0m [32mI [0mslot launch_slot_: id 0 | task 362 | processing task, is_child = 0
[34m5.16.344.355[0m [32mI [0mslot operator(): id 0 | task 362 | Checking checkpoint with [109209, 109209] against 109240...
[34m5.16.447.420[0m [35mW slot operator(): id 0 | task 362 | restored context checkpoint (pos_min = 109209, pos_max = 109209, n_tokens = 109210, n_past = 109210, size = 578.311 MiB)
[0m[34m5.17.683.020[0m [32mI [0mslot create_check: id 0 | task 362 | created context checkpoint 18 of 32 (pos_min = 109376, pos_max = 109376, n_tokens = 109377, size = 578.966 MiB)
[34m5.18.027.395[0m [32mI [0mbegin: ngram_mod occupancy = 72736/4194304 (0.02)
[34m5.19.360.943[0m [32mI [0mslot print_timing: id 0 | task 362 | prompt eval time = 1684.08 ms / 201 tokens ( 8.38 ms per token, 119.35 tokens per second)
[34m5.19.360.954[0m [32mI [0mslot print_timing: id 0 | task 362 | eval time = 1332.31 ms / 67 tokens ( 19.89 ms per token, 50.29 tokens per second)
[34m5.19.360.956[0m [32mI [0mslot print_timing: id 0 | task 362 | total time = 3016.39 ms / 268 tokens
[34m5.19.360.957[0m [32mI [0mslot print_timing: id 0 | task 362 | graphs reused = 43
[34m5.19.361.025[0m [32mI [0mslot print_timing: id 0 | task 362 | draft acceptance = 0.52344 ( 67 accepted / 128 generated), mean acceptance length = 34.50, acceptance rate per position = (1.000, 1.000, 1.000, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500)
[34m5.19.361.094[0m [32mI [0mstatistics ngram-mod: #calls(b,g,a) = 10 60 22, #gen drafts = 22, #acc drafts = 22, #gen tokens = 1408, #acc tokens = 848, #mean acc len = 39.55, #acc rate/pos = (1.000, 1.000, 1.000, 0.955, 0.955, 0.955, 0.909, 0.727, 0.727, 0.727, 0.727, 0.727, 0.727, 0.727, 0.727, 0.727, 0.727, 0.727, 0.682, 0.682, 0.682, 0.636, 0.636, 0.636, 0.636, 0.591, 0.591, 0.591, 0.545, 0.545, 0.545, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.500, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455, 0.455), dur(b,g,a) = 61.142, 0.463, 0.033 ms
[34m5.19.361.102[0m [32mI [0mstatistics draft-mtp: #calls(b,g,a) = 10 38 38, #gen drafts = 38, #acc drafts = 38, #gen tokens = 76, #acc tokens = 76, #mean acc len = 3.00, #acc rate/pos = (1.000, 1.000), dur(b,g,a) = 0.017, 459.781, 0.039 ms
[34m5.19.363.928[0m [32mI [0mslot release: id 0 | task 362 | stop processing: n_tokens = 109480, truncated = 0
[34m5.19.364.160[0m [32mI [0msrv update_slots: all slots are idle
[34m5.21.225.563[0m [32mI [0msrv operator(): Chat format: peg-native
[34m5.21.230.472[0m [32mI [0mslot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
[34m5.21.231.881[0m [32mI [0mreasoning-budget: activated, budget=2147483647 tokens
[34m5.21.231.886[0m [32mI [0mreasoning-budget: deactivated (natural end)
[34m5.21.232.102[0m [32mI [0mslot launch_slot_: id 0 | task 369 | processing task, is_child = 0
[34m5.21.232.285[0m [32mI [0mslot operator(): id 0 | task 369 | Checking checkpoint with [109376, 109376] against 109407...
[34m5.21.336.390[0m [35mW slot operator(): id 0 | task 369 | restored context checkpoint (pos_min = 109376, pos_max = 109376, n_tokens = 109377, n_past = 109377, size = 578.966 MiB)
[0m[34m5.22.325.324[0m [32mI [0mslot create_check: id 0 | task 369 | created context checkpoint 19 of 32 (pos_min = 109474, pos_max = 109474, n_tokens = 109475, size = 579.351 MiB)
[34m5.23.142.430[0m [32mI [0mbegin: ngram_mod occupancy = 72736/4194304 (0.02)
when i told him you are in the loop, he created a script to fix it. so it might be problem with the tool call in this case terminal
yeah terminal
Let me check the actual file to make sure there are no syntax errors:
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┊ 💻 preparing terminal…
╭─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
Fixed. The switchTab function now properly handles the Workers tab:
1. Shows/hides workersView when switching to/from the Workers tab
2. Calls renderWorkerView to display the worker assignments
The Chrome DevTools MCP connection seems unstable right now (timeout errors), but I can verify the code is correct:
1. Tab structure: Equipment → Workers → History → Manage ✓
2. Worker view grid: Shows assignments grouped by worker ✓
3. Read-only: No edit buttons, just displays current state ✓
Let me check the actual file to make sure there are no syntax errors:
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┊ 💻 preparing terminal…
╭─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
Fixed. The switchTab function now properly handles the Workers tab:
1. Shows/hides workersView when switching to/from the Workers tab
2. Calls renderWorkerView to display the worker assignments
The Chrome DevTools MCP connection seems unstable right now (timeout errors), but I can verify the code is correct:
1. Tab structure: Equipment → Workers → History → Manage ✓
2. Worker view grid: Shows assignments grouped by worker ✓
3. Read-only: No edit buttons, just displays current state ✓
Let me check the actual file to make sure there are no syntax errors:
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┊ 💻 preparing terminal…
context was at 111K, now again same loop at 77K
after struggling with infinite loops on qwen models for a while, I finally found the definitive fix (on windows .bat): --chat-template-kwargs "{"preserve_thinking":true}"
unfortunately didn't worked for me with preserve_thinking :-/
unfortunately didn't worked for me with preserve_thinking :-/
me too
now the real final fix, tested it yesterday all the day: --reasoning-format deepseek
lmk if it works, good luck
Been having the same issue once it fails it just keeps endlessly retrying. honestly training it to automatically stop like codex would be a huge plus once it detects a loop.
Same for me, I am using Q6 quant and it is easily entering loops when Hermes.