[GH-ISSUE #264] 500th request to HTTP API gets rejected #113

Closed
opened 2026-04-12 09:39:01 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @drhino on GitHub (Aug 2, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/264

Originally assigned to: @BruceMacD on GitHub.

At the 500th request of batch processing using the ollama http api (ollama running using the .app)
that 500th request fails to open. Immediately after the failed request, the next request succeeds. It's unclear whether the ollama server is restarted or not after that failure. The noticable part in the server.log is:

...
llama_model_load_internal: ftype      = 2 (mostly Q4_0)
llama_model_load_internal: n_ff       = 8640
llama_model_load_internal: model size = 3B
llama_model_load_internal: ggml ctx size =    0.06 MB
llama_model_load_internal: mem required  = 2870.72 MB (+  682.00 MB per state)
llama_new_context_with_model: kv self size  =  650.00 MB
ggml_metal_init: allocating
Context leak detected, msgtracer returned -1
ggml_metal_init: using MPS
ggml_metal_init: loading '/Applications/Ollama.app/Contents/Resources/ggml-metal.metal'
ggml_metal_init: loaded kernel_add                            0x153796ec0
ggml_metal_init: loaded kernel_mul                            0x153797120
ggml_metal_init: loaded kernel_mul_row                        0x153797380
ggml_metal_init: loaded kernel_scale                          0x1537975e0
ggml_metal_init: loaded kernel_silu                           0x153797840
ggml_metal_init: loaded kernel_relu                           0x153797aa0
ggml_metal_init: loaded kernel_gelu                           0x153797d00
ggml_metal_init: loaded kernel_soft_max                       0x153797f60
ggml_metal_init: loaded kernel_diag_mask_inf                  0x1537981c0
ggml_metal_init: loaded kernel_get_rows_f16                   0x153798420
ggml_metal_init: loaded kernel_get_rows_q4_0                  0x153798680
ggml_metal_init: loaded kernel_get_rows_q4_1                  0x1537988e0
ggml_metal_init: loaded kernel_get_rows_q2_K                  0x153798b40
ggml_metal_init: loaded kernel_get_rows_q3_K                  0x153798da0
ggml_metal_init: loaded kernel_get_rows_q4_K                  0x153799000
ggml_metal_init: loaded kernel_get_rows_q5_K                  0x153799260
ggml_metal_init: loaded kernel_get_rows_q6_K                  0x1537994c0
ggml_metal_init: loaded kernel_rms_norm                       0x153799720
ggml_metal_init: loaded kernel_norm                           0x153799980
ggml_metal_init: loaded kernel_mul_mat_f16_f32                0x153799be0
ggml_metal_init: loaded kernel_mul_mat_q4_0_f32               0x153799e40
ggml_metal_init: loaded kernel_mul_mat_q4_1_f32               0x15379a0a0
ggml_metal_init: loaded kernel_mul_mat_q2_K_f32               0x15379a300
ggml_metal_init: loaded kernel_mul_mat_q3_K_f32               0x15379b120
ggml_metal_init: loaded kernel_mul_mat_q4_K_f32               0x15379b380
ggml_metal_init: loaded kernel_mul_mat_q5_K_f32               0x15379b5e0
ggml_metal_init: loaded kernel_mul_mat_q6_K_f32               0x15379b840
ggml_metal_init: loaded kernel_rope                           0x15379baa0
ggml_metal_init: loaded kernel_alibi_f32                      0x15379bd00
ggml_metal_init: loaded kernel_cpy_f32_f16                    0x15379bf60
ggml_metal_init: loaded kernel_cpy_f32_f32                    0x15379c1c0
ggml_metal_init: loaded kernel_cpy_f16_f16                    0x15379c420
ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB
ggml_metal_init: hasUnifiedMemory             = true
ggml_metal_init: maxTransferRate              = built-in GPU
ggml_metal_add_buffer: allocated 'data            ' buffer, size =  1839.12 MB, ( 1841.56 / 10922.67)
ggml_metal_add_buffer: allocated 'eval            ' buffer, size =   520.00 MB, ( 2361.56 / 10922.67)
ggml_metal_add_buffer: allocated 'kv              ' buffer, size =   652.00 MB, ( 3013.56 / 10922.67)
ggml_metal_add_buffer: allocated 'scr0            ' buffer, size =   256.00 MB, ( 3269.56 / 10922.67)
ggml_metal_add_buffer: allocated 'scr1            ' buffer, size =   256.00 MB, ( 3525.56 / 10922.67)
2023-08-03 01:24:10.990 ollama[3006:24871] *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: '*** -[__NSArrayM setObject:atIndexedSubscript:]: object cannot be nil'
*** First throw call stack:
(
  0   CoreFoundation                      0x00000001aa66b154 __exceptionPreprocess + 176
  1   libobjc.A.dylib                     0x00000001aa18a4d4 objc_exception_throw + 60
  2   CoreFoundation                      0x00000001aa7559b8 -[__NSCFString characterAtIndex:].cold.1 + 0
  3   CoreFoundation                      0x00000001aa752280 -[__NSArrayM setObject:atIndexedSubscript:].cold.2 + 0
  4   CoreFoundation                      0x00000001aa609f60 -[__NSArrayM setObject:atIndexedSubscript:] + 640
  5   ollama                              0x00000001005b258c ggml_metal_graph_compute + 108
  6   ollama                              0x00000001005a56c4 _ZL19llama_eval_internalR13llama_contextPKiPKfiiiPKc + 2620
  7   ollama                              0x00000001005a4c58 llama_eval + 40
  8   ollama                              0x0000000100570228 _cgo_2053a7d5fdc2_Cfunc_llama_eval + 44
  9   ollama                              0x00000001000be05c runtime.asmcgocall.abi0 + 124
)
libc++abi: terminating due to uncaught exception of type NSException
nsor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
llama_new_context_with_model: max tensor size =    54.93 MB
SIGABRT: abort
PC=0x1aa4dc764 m=0 sigcode=0
signal arrived during cgo execution

goroutine 1107 [syscall]:
runtime.cgocall(0x1005701fc, 0x14000163278)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/cgocall.go:157 +0x54 fp=0x14000163240 sp=0x14000163200 pc=0x10005ae24
github.com/jmorganca/ollama/llama._Cfunc_llama_eval(0x144057800, 0x1400043ebf0, 0x1, 0x0, 0x8)
  _cgo_gotypes.go:210 +0x38 fp=0x14000163270 sp=0x14000163240 pc=0x10055bee8
github.com/jmorganca/ollama/llama.New.func4(0x10079afa0?, {0x1400043ebf0, 0x1, 0x0?}, {0xffffffffffffffff, 0x0, 0x800, 0x200, 0x1, 0x0, ...})
  /Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x7c fp=0x140001632c0 sp=0x14000163270 pc=0x10055cd0c
github.com/jmorganca/ollama/llama.New({0x1400007c0e0, 0x65}, {0xffffffffffffffff, 0x0, 0x800, 0x200, 0x1, 0x0, 0x0, 0x1, ...})
  /Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x288 fp=0x14000163480 sp=0x140001632c0 pc=0x10055cac8
github.com/jmorganca/ollama/server.GenerateHandler(0x1400046a700)
/Users/jmorgan/workspace/ollama/server/routes.go:56 +0x5c0 fp=0x140001636e0 sp=0x14000163480 pc=0x100569110
github.com/gin-gonic/gin.(*Context).Next(...)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174
github.com/gin-gonic/gin.CustomRecoveryWithWriter.func1(0x1400046a700)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/recovery.go:102 +0x7c fp=0x14000163730 sp=0x140001636e0 pc=0x100550f6c
github.com/gin-gonic/gin.(*Context).Next(...)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174
github.com/gin-gonic/gin.LoggerWithConfig.func1(0x1400046a700)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/logger.go:240 +0xac fp=0x140001638e0 sp=0x14000163730 pc=0x1005501ec
github.com/gin-gonic/gin.(*Context).Next(...)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174
github.com/gin-gonic/gin.(*Engine).handleHTTPRequest(0x1400014dba0, 0x1400046a700)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:620 +0x54c fp=0x14000163a70 sp=0x140001638e0 pc=0x10054f2fc
github.com/gin-gonic/gin.(*Engine).ServeHTTP(0x1400014dba0, {0x1007ed480?, 0x140001741c0}, 0x1400046a400)
  /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:576 +0x1d4 fp=0x14000163ab0 sp=0x14000163a70 pc=0x10054ec04
net/http.serverHandler.ServeHTTP(
{0x1007eb2f0?}, {0x1007ed480, 0x140001741c0}, 0x1400046a400)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:2936 +0x2d8 fp=0x14000163b60 sp=0x14000163ab0 pc=0x1002d8858
net/http.(*conn).serve(0x140001242d0, {0x1007edaf8, 0x1400046c240})
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:1995 +0x560 fp=0x14000163fa0 sp=0x14000163b60 pc=0x1002d4550
net/http.(*Server).Serve.func3()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x30 fp=0x14000163fd0 sp=0x14000163fa0 pc=0x1002d9080
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000163fd0 sp=0x14000163fd0 pc=0x1000be234
created by net/http.(*Server).Serve
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x520

goroutine 1 [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000593700 sp=0x140005936e0 pc=0x10008e0a4
runtime.netpollblock(0x14000593798?, 0x141fb4?, 0x1?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x14000593740 sp=0x14000593700 pc=0x1000875c8
internal/poll.runtime_pollWait(0x1282b9a18, 0x72)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x14000593770 sp=0x14000593740 pc=0x1000b7e00
internal/poll.(*pollDesc).wait(0x14000448680?, 0x1000637a8?, 0x0)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140005937a0 sp=0x14000593770 pc=0x10013d5f8
internal/poll.(*pollDesc).waitRead(...)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x14000448680)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go:614 +0x250 fp=0x14000593850 sp=0x140005937a0 pc=0x1001420a0
net.(*netFD).accept(0x14000448680)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_unix.go:172 +0x28 fp=0x14000593910 sp=0x14000593850 pc=0x100181748
net.(*TCPListener).accept(0x1400000ed50)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock_posix.go:148 +0x28 fp=0x14000593940 sp=0x14000593910 pc=0x100196d48
net.(*TCPListener).Accept(0x1400000ed50)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock.go:297 +0x2c fp=0x14000593980 sp=0x14000593940 pc=0x100195ebc
net/http.(*onceCloseListener).Accept(0x140001242d0?)
  <autogenerated>:1 +0x30 fp=0x140005939a0
sp=0x14000593980 pc=0x1002fc800
net/http.(*Server).Serve(0x14000364ff0, {0x1007ed270, 0x1400000ed50})
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3059 +0x304 fp=0x14000593ad0 sp=0x140005939a0 pc=0x1002d8d24
github.com/jmorganca/ollama/server.Serve({0x1007ed270, 0x1400000ed50})
  /Users/jmorgan/workspace/ollama/server/routes.go:281 +0x524 fp=0x14000593ca0 sp=0x14000593ad0 pc=0x10056b6a4
github.com/jmorganca/ollama/cmd.RunServer(0x1400041b200?, {0x1005c1bac?, 0x0?, 0x0?})
/Users/jmorgan/workspace/ollama/cmd/cmd.go:434 +0x114 fp=0x14000593d20 sp=0x14000593ca0 pc=0x10056f2e4
github.com/spf13/cobra.(*Command).execute(0x1400041b200, {0x100c6a470, 0x0, 0x0})
  /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x5c8 fp=0x14000593e60 sp=0x14000593d20 pc=0x10037ef68
github.com/spf13/cobra.(*Command).ExecuteC(0x1400041a900)
  /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x35c fp=0x14000593f20 sp=0x14000593e60 pc=0x10037f6bc
github.com/spf13/cobra.(*Command).Execute(...)
  /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(0x14000054768?, {0x1007eda88?, 0x1400002a0e0?})
  /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 +0x50 fp=0x14000593f40 sp=0x14000593f20 pc=0x10037f250
main.main()
  /Users/jmorgan/workspace/ollama/main.go:10 +0x34 fp=0x14000593f70 sp=0x14000593f40 pc=0x10056ffc4
runtime.main()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:250 +0x248 fp=0x14000593fd0 sp=0x14000593f70 pc=0x10008dc78
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000593fd0 sp=0x14000593fd0 pc=0x1000be234

goroutine 2 [force gc (idle), 37 minutes]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054fa0 sp=0x14000054f80 pc=0x10008e0a4
runtime.goparkunlock(...)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387
runtime.forcegchelper()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:305 +0xb8 fp=0x14000054fd0 sp=0x14000054fa0 pc=0x10008dee8
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000054fd0 sp=
0x14000054fd0 pc=0x1000be234
created by runtime.init.6
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:293 +0x24

goroutine 3 [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055760 sp=0x14000055740 pc=0x10008e0a4
runtime.goparkunlock(...)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387
runtime.bgsweep(0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcsweep.go:319 +0x110 fp=0x140000557b0 sp=0x14000055760 pc=0x10007adf0
runtime.gcenable.func1()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x28 fp=0x140000557d0 sp=0x140000557b0 pc=0x10006f898
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000557d0 sp=0x140000557d0 pc=0x1000be234
created by runtime.gcenable
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x74

goroutine 4 [GC scavenge wait]:
runtime.gopark(0x2e7de80?, 0x6553f100?, 0x0?, 0x0?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055f50 sp=0x14000055f30 pc=0x10008e0a4
runtime.goparkunlock(...)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:
387
runtime.(*scavengerState).park(0x100baef40)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:400 +0x5c fp=0x14000055f80 sp=0x14000055f50 pc=0x100078bfc
runtime.bgscavenge(0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:633 +0xac fp=0x14000055fb0 sp=0x14000055f80 pc=0x1000791dc
runtime.gcenable.func2()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +0x28 fp=0x14000055fd0 sp=0x14000055fb0 pc=0x10006f838
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000055fd0 sp=0x14000055fd0 pc=0x1000be234
created by runtime.gcenable
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +
0xb8

goroutine 5 [finalizer wait, 37 minutes]:
runtime.gopark(0x1a0?, 0x100baf980?, 0xc0?, 0x36?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054580 sp=0x14000054560 pc=0x10008e0a4
runtime.runfinq()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:193 +0x10c fp=0x140000547d0 sp=0x14000054580 pc=0x10006e92c
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000547d0 sp=0x140000547d0 pc=0x1000be234
created by runtime.createfing
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:163 +0x84

goroutine 18 [GC worker (idle)
]:
runtime.gopark(0x3ef46395813?, 0x3?, 0x8a?, 0xee?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000056f40 sp=0x14000056f20 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000056fd0 sp=0x14000056f40 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000056fd0 sp=0x14000056fd0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 9 [GC worker (idle)]:
runtime.gopark(0x3ebaad96151
?, 0x3?, 0xbf?, 0xdb?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000057740 sp=0x14000057720 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000577d0 sp=0x14000057740 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000577d0 sp=0x140000577d0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 19 [GC worker (idle)]:
runtime.gopark(0x3ef3fe69e5c?, 0x1?, 0xa1?, 0xfa?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go
:381 +0xe4 fp=0x14000050740 sp=0x14000050720 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000507d0 sp=0x14000050740 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000507d0 sp=0x140000507d0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 20 [GC worker (idle)]:
runtime.gopark(0x3ef463d05cf?, 0x3?, 0x9b?, 0x90?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000050f40 sp=0x14000050f20 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000050fd0 sp=0x14000050f40
pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000050fd0 sp=0x14000050fd0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 34 [GC worker (idle)]:
runtime.gopark(0x3ef463b14bd?, 0x1?, 0xb1?, 0x96?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000094740 sp=0x14000094720 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000947d0 sp=0x14000094740 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000947d0 sp=0x140000947d0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 35 [GC worker (idle)]:
runtime.gopark(0x3ef0e621f41?, 0x3?, 0x2e?, 0x17?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000094f40 sp=0x14000094f20 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000094fd0 sp=0x14000094f40 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000094fd0 sp=0x14000094fd0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 10 [GC worker (idle)]:
runtime.gopark(0x3ef0e6222ac?, 0x3?, 0x95?, 0xfe?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000057f40 sp=0x14000057f20 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000057fd0 sp=0x14000057f40 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000057fd0 sp=0x14000057fd0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 36 [GC worker (idle)]:
runtime.gopark(0x3ef4650b3bb?, 0x1?, 0xf8?, 0xa5?
, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000095740 sp=0x14000095720 pc=0x10008e0a4
runtime.gcBgMarkWorker()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000957d0 sp=0x14000095740 pc=0x1000717dc
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000957d0 sp=0x140000957d0 pc=0x1000be234
created by runtime.gcBgMarkStartWorkers
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28

goroutine 1108 [IO wait]:
runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x1000d0b90?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000052d40 sp=0x14000052d20
pc=0x10008e0a4
runtime.netpollblock(0x0?, 0x0?, 0x0?)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x14000052d80 sp=0x14000052d40 pc=0x1000875c8
internal/poll.runtime_pollWait(0x1282b9838, 0x72)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x14000052db0 sp=0x14000052d80 pc=0x1000b7e00
internal/poll.(*pollDesc).wait(0x14000448000?, 0x140001b23a1?, 0x0)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000052de0 sp=0x14000052db0 pc=0x10013d5f8
internal/poll.(*pollDesc).waitRead(...)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x14000448000, {0x140001b23a1, 0x1, 0x1})
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go
:167 +0x200 fp=0x14000052e80 sp=0x14000052de0 pc=0x10013e960
net.(*netFD).Read(0x14000448000, {0x140001b23a1?, 0x14000052f90?, 0x14000120be0?})
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_posix.go:55 +0x28 fp=0x14000052ed0 sp=0x14000052e80 pc=0x10017faa8
net.(*conn).Read(0x14000518020, {0x140001b23a1?, 0x0?, 0x0?})
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/net.go:183 +0x34 fp=0x14000052f20 sp=0x14000052ed0 pc=0x10018e0b4
net.(*TCPConn).Read(
0x0?, {0x140001b23a1?, 0x0?, 0x1005696a0?})
  <autogenerated>:1 +0x2c fp=0x14000052f50 sp=0x14000052f20 pc=0x1001a05fc
net/http.(*connReader).backgroundRead(0x140001b2390)
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:674 +0x44 fp=0x14000052fb0 sp=0x14000052f50 pc=0x1002cea04
net/http.(*connReader).startBackgroundRead.func2()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0x28 fp=0x14000052fd0 sp=0x14000052fb0 pc=0x1002ce928
runtime.goexit()
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000052fd0 sp=0x14000052fd0 pc=0x1000be234
created by net/http.(*connReader).startBackgroundRead
  /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0xcc
r0      0x0
r1      0x0
r2      0x0
r3      0x0
r4      0x1aa4d0647
r5      0x16fd91d90
r6      0x6e
r7      0x200
r8      0x5cdc9440437c471f
r9      0x5cdc94424625279f
r10     0x200
r11     0xb
r12     0xb
r13     0x0
r14     0x0
r15     0x0
r16     0x148
r17     0x20a0bb3a0
r18     0x0
r19     0x6
r20     0x205596080
r21     0x103
r22     0x205596160
r23     0x15379cde0
r24     0x1
r25     0x1508c40a0
r26     0x1
r27     0x20
r28     0x16fdab0f8
r29     0x16fd91d00
lr      0x1aa513c28
sp      0x16fd91ce0
pc      0x1aa4dc764
fault   0x1aa4dc764
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
- using env:	export GIN_MODE=release
- using code:	gin.SetMode(gin.ReleaseMode)

[GIN-debug] GET    /                         --> github.com/jmorganca/ollama/server.Serve.func1 (4 handlers)
[GIN-debug] POST   /api/pull                 --> github.com/jmorganca/ollama/server.PullModelHandler (4 handlers)
[GIN-debug] POST   /api/generate             --> github.com/jmorganca/ollama/server.GenerateHandler (4 handlers)
[GIN-debug] POST   /api/create               --> github.com/jmorganca/ollama/server.CreateModelHandler (4 handlers)
[GIN-debug] POST   /api/push                 --> github.com/jmorganca/ollama/server.PushModelHandler (4 handlers)
[GIN-debug] POST   /api/copy                 --> github.com/jmorganca/ollama/server.CopyModelHandler (4 handlers)
[GIN-debug] GET    /api/tags                 --> github.com/jmorganca/ollama/server.ListModelsHandler (4 handlers)
[GIN-debug] DELETE /api/delete               --> github.com/jmorganca/ollama/server.DeleteModelHandler (4 handlers)
2023/08/03 01:24:14 routes.go:276: Listening on 127.0.0.1:11434

Originally created by @drhino on GitHub (Aug 2, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/264 Originally assigned to: @BruceMacD on GitHub. At the 500th request of batch processing using the ollama http api (ollama running using the .app) that 500th request fails to open. Immediately after the failed request, the next request succeeds. It's unclear whether the ollama server is restarted or not after that failure. The noticable part in the server.log is: ``` ... llama_model_load_internal: ftype = 2 (mostly Q4_0) llama_model_load_internal: n_ff = 8640 llama_model_load_internal: model size = 3B llama_model_load_internal: ggml ctx size = 0.06 MB llama_model_load_internal: mem required = 2870.72 MB (+ 682.00 MB per state) llama_new_context_with_model: kv self size = 650.00 MB ggml_metal_init: allocating Context leak detected, msgtracer returned -1 ggml_metal_init: using MPS ggml_metal_init: loading '/Applications/Ollama.app/Contents/Resources/ggml-metal.metal' ggml_metal_init: loaded kernel_add 0x153796ec0 ggml_metal_init: loaded kernel_mul 0x153797120 ggml_metal_init: loaded kernel_mul_row 0x153797380 ggml_metal_init: loaded kernel_scale 0x1537975e0 ggml_metal_init: loaded kernel_silu 0x153797840 ggml_metal_init: loaded kernel_relu 0x153797aa0 ggml_metal_init: loaded kernel_gelu 0x153797d00 ggml_metal_init: loaded kernel_soft_max 0x153797f60 ggml_metal_init: loaded kernel_diag_mask_inf 0x1537981c0 ggml_metal_init: loaded kernel_get_rows_f16 0x153798420 ggml_metal_init: loaded kernel_get_rows_q4_0 0x153798680 ggml_metal_init: loaded kernel_get_rows_q4_1 0x1537988e0 ggml_metal_init: loaded kernel_get_rows_q2_K 0x153798b40 ggml_metal_init: loaded kernel_get_rows_q3_K 0x153798da0 ggml_metal_init: loaded kernel_get_rows_q4_K 0x153799000 ggml_metal_init: loaded kernel_get_rows_q5_K 0x153799260 ggml_metal_init: loaded kernel_get_rows_q6_K 0x1537994c0 ggml_metal_init: loaded kernel_rms_norm 0x153799720 ggml_metal_init: loaded kernel_norm 0x153799980 ggml_metal_init: loaded kernel_mul_mat_f16_f32 0x153799be0 ggml_metal_init: loaded kernel_mul_mat_q4_0_f32 0x153799e40 ggml_metal_init: loaded kernel_mul_mat_q4_1_f32 0x15379a0a0 ggml_metal_init: loaded kernel_mul_mat_q2_K_f32 0x15379a300 ggml_metal_init: loaded kernel_mul_mat_q3_K_f32 0x15379b120 ggml_metal_init: loaded kernel_mul_mat_q4_K_f32 0x15379b380 ggml_metal_init: loaded kernel_mul_mat_q5_K_f32 0x15379b5e0 ggml_metal_init: loaded kernel_mul_mat_q6_K_f32 0x15379b840 ggml_metal_init: loaded kernel_rope 0x15379baa0 ggml_metal_init: loaded kernel_alibi_f32 0x15379bd00 ggml_metal_init: loaded kernel_cpy_f32_f16 0x15379bf60 ggml_metal_init: loaded kernel_cpy_f32_f32 0x15379c1c0 ggml_metal_init: loaded kernel_cpy_f16_f16 0x15379c420 ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: maxTransferRate = built-in GPU ggml_metal_add_buffer: allocated 'data ' buffer, size = 1839.12 MB, ( 1841.56 / 10922.67) ggml_metal_add_buffer: allocated 'eval ' buffer, size = 520.00 MB, ( 2361.56 / 10922.67) ggml_metal_add_buffer: allocated 'kv ' buffer, size = 652.00 MB, ( 3013.56 / 10922.67) ggml_metal_add_buffer: allocated 'scr0 ' buffer, size = 256.00 MB, ( 3269.56 / 10922.67) ggml_metal_add_buffer: allocated 'scr1 ' buffer, size = 256.00 MB, ( 3525.56 / 10922.67) 2023-08-03 01:24:10.990 ollama[3006:24871] *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: '*** -[__NSArrayM setObject:atIndexedSubscript:]: object cannot be nil' *** First throw call stack: ( 0 CoreFoundation 0x00000001aa66b154 __exceptionPreprocess + 176 1 libobjc.A.dylib 0x00000001aa18a4d4 objc_exception_throw + 60 2 CoreFoundation 0x00000001aa7559b8 -[__NSCFString characterAtIndex:].cold.1 + 0 3 CoreFoundation 0x00000001aa752280 -[__NSArrayM setObject:atIndexedSubscript:].cold.2 + 0 4 CoreFoundation 0x00000001aa609f60 -[__NSArrayM setObject:atIndexedSubscript:] + 640 5 ollama 0x00000001005b258c ggml_metal_graph_compute + 108 6 ollama 0x00000001005a56c4 _ZL19llama_eval_internalR13llama_contextPKiPKfiiiPKc + 2620 7 ollama 0x00000001005a4c58 llama_eval + 40 8 ollama 0x0000000100570228 _cgo_2053a7d5fdc2_Cfunc_llama_eval + 44 9 ollama 0x00000001000be05c runtime.asmcgocall.abi0 + 124 ) libc++abi: terminating due to uncaught exception of type NSException nsor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB llama_new_context_with_model: max tensor size = 54.93 MB SIGABRT: abort PC=0x1aa4dc764 m=0 sigcode=0 signal arrived during cgo execution goroutine 1107 [syscall]: runtime.cgocall(0x1005701fc, 0x14000163278) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/cgocall.go:157 +0x54 fp=0x14000163240 sp=0x14000163200 pc=0x10005ae24 github.com/jmorganca/ollama/llama._Cfunc_llama_eval(0x144057800, 0x1400043ebf0, 0x1, 0x0, 0x8) _cgo_gotypes.go:210 +0x38 fp=0x14000163270 sp=0x14000163240 pc=0x10055bee8 github.com/jmorganca/ollama/llama.New.func4(0x10079afa0?, {0x1400043ebf0, 0x1, 0x0?}, {0xffffffffffffffff, 0x0, 0x800, 0x200, 0x1, 0x0, ...}) /Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x7c fp=0x140001632c0 sp=0x14000163270 pc=0x10055cd0c github.com/jmorganca/ollama/llama.New({0x1400007c0e0, 0x65}, {0xffffffffffffffff, 0x0, 0x800, 0x200, 0x1, 0x0, 0x0, 0x1, ...}) /Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x288 fp=0x14000163480 sp=0x140001632c0 pc=0x10055cac8 github.com/jmorganca/ollama/server.GenerateHandler(0x1400046a700) /Users/jmorgan/workspace/ollama/server/routes.go:56 +0x5c0 fp=0x140001636e0 sp=0x14000163480 pc=0x100569110 github.com/gin-gonic/gin.(*Context).Next(...) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 github.com/gin-gonic/gin.CustomRecoveryWithWriter.func1(0x1400046a700) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/recovery.go:102 +0x7c fp=0x14000163730 sp=0x140001636e0 pc=0x100550f6c github.com/gin-gonic/gin.(*Context).Next(...) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 github.com/gin-gonic/gin.LoggerWithConfig.func1(0x1400046a700) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/logger.go:240 +0xac fp=0x140001638e0 sp=0x14000163730 pc=0x1005501ec github.com/gin-gonic/gin.(*Context).Next(...) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 github.com/gin-gonic/gin.(*Engine).handleHTTPRequest(0x1400014dba0, 0x1400046a700) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:620 +0x54c fp=0x14000163a70 sp=0x140001638e0 pc=0x10054f2fc github.com/gin-gonic/gin.(*Engine).ServeHTTP(0x1400014dba0, {0x1007ed480?, 0x140001741c0}, 0x1400046a400) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:576 +0x1d4 fp=0x14000163ab0 sp=0x14000163a70 pc=0x10054ec04 net/http.serverHandler.ServeHTTP( {0x1007eb2f0?}, {0x1007ed480, 0x140001741c0}, 0x1400046a400) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:2936 +0x2d8 fp=0x14000163b60 sp=0x14000163ab0 pc=0x1002d8858 net/http.(*conn).serve(0x140001242d0, {0x1007edaf8, 0x1400046c240}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:1995 +0x560 fp=0x14000163fa0 sp=0x14000163b60 pc=0x1002d4550 net/http.(*Server).Serve.func3() /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x30 fp=0x14000163fd0 sp=0x14000163fa0 pc=0x1002d9080 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000163fd0 sp=0x14000163fd0 pc=0x1000be234 created by net/http.(*Server).Serve /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x520 goroutine 1 [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000593700 sp=0x140005936e0 pc=0x10008e0a4 runtime.netpollblock(0x14000593798?, 0x141fb4?, 0x1?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x14000593740 sp=0x14000593700 pc=0x1000875c8 internal/poll.runtime_pollWait(0x1282b9a18, 0x72) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x14000593770 sp=0x14000593740 pc=0x1000b7e00 internal/poll.(*pollDesc).wait(0x14000448680?, 0x1000637a8?, 0x0) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140005937a0 sp=0x14000593770 pc=0x10013d5f8 internal/poll.(*pollDesc).waitRead(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x14000448680) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go:614 +0x250 fp=0x14000593850 sp=0x140005937a0 pc=0x1001420a0 net.(*netFD).accept(0x14000448680) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_unix.go:172 +0x28 fp=0x14000593910 sp=0x14000593850 pc=0x100181748 net.(*TCPListener).accept(0x1400000ed50) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock_posix.go:148 +0x28 fp=0x14000593940 sp=0x14000593910 pc=0x100196d48 net.(*TCPListener).Accept(0x1400000ed50) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock.go:297 +0x2c fp=0x14000593980 sp=0x14000593940 pc=0x100195ebc net/http.(*onceCloseListener).Accept(0x140001242d0?) <autogenerated>:1 +0x30 fp=0x140005939a0 sp=0x14000593980 pc=0x1002fc800 net/http.(*Server).Serve(0x14000364ff0, {0x1007ed270, 0x1400000ed50}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3059 +0x304 fp=0x14000593ad0 sp=0x140005939a0 pc=0x1002d8d24 github.com/jmorganca/ollama/server.Serve({0x1007ed270, 0x1400000ed50}) /Users/jmorgan/workspace/ollama/server/routes.go:281 +0x524 fp=0x14000593ca0 sp=0x14000593ad0 pc=0x10056b6a4 github.com/jmorganca/ollama/cmd.RunServer(0x1400041b200?, {0x1005c1bac?, 0x0?, 0x0?}) /Users/jmorgan/workspace/ollama/cmd/cmd.go:434 +0x114 fp=0x14000593d20 sp=0x14000593ca0 pc=0x10056f2e4 github.com/spf13/cobra.(*Command).execute(0x1400041b200, {0x100c6a470, 0x0, 0x0}) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x5c8 fp=0x14000593e60 sp=0x14000593d20 pc=0x10037ef68 github.com/spf13/cobra.(*Command).ExecuteC(0x1400041a900) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x35c fp=0x14000593f20 sp=0x14000593e60 pc=0x10037f6bc github.com/spf13/cobra.(*Command).Execute(...) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(0x14000054768?, {0x1007eda88?, 0x1400002a0e0?}) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 +0x50 fp=0x14000593f40 sp=0x14000593f20 pc=0x10037f250 main.main() /Users/jmorgan/workspace/ollama/main.go:10 +0x34 fp=0x14000593f70 sp=0x14000593f40 pc=0x10056ffc4 runtime.main() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:250 +0x248 fp=0x14000593fd0 sp=0x14000593f70 pc=0x10008dc78 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000593fd0 sp=0x14000593fd0 pc=0x1000be234 goroutine 2 [force gc (idle), 37 minutes]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054fa0 sp=0x14000054f80 pc=0x10008e0a4 runtime.goparkunlock(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387 runtime.forcegchelper() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:305 +0xb8 fp=0x14000054fd0 sp=0x14000054fa0 pc=0x10008dee8 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000054fd0 sp= 0x14000054fd0 pc=0x1000be234 created by runtime.init.6 /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:293 +0x24 goroutine 3 [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055760 sp=0x14000055740 pc=0x10008e0a4 runtime.goparkunlock(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387 runtime.bgsweep(0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcsweep.go:319 +0x110 fp=0x140000557b0 sp=0x14000055760 pc=0x10007adf0 runtime.gcenable.func1() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x28 fp=0x140000557d0 sp=0x140000557b0 pc=0x10006f898 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000557d0 sp=0x140000557d0 pc=0x1000be234 created by runtime.gcenable /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x74 goroutine 4 [GC scavenge wait]: runtime.gopark(0x2e7de80?, 0x6553f100?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055f50 sp=0x14000055f30 pc=0x10008e0a4 runtime.goparkunlock(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go: 387 runtime.(*scavengerState).park(0x100baef40) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:400 +0x5c fp=0x14000055f80 sp=0x14000055f50 pc=0x100078bfc runtime.bgscavenge(0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:633 +0xac fp=0x14000055fb0 sp=0x14000055f80 pc=0x1000791dc runtime.gcenable.func2() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +0x28 fp=0x14000055fd0 sp=0x14000055fb0 pc=0x10006f838 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000055fd0 sp=0x14000055fd0 pc=0x1000be234 created by runtime.gcenable /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 + 0xb8 goroutine 5 [finalizer wait, 37 minutes]: runtime.gopark(0x1a0?, 0x100baf980?, 0xc0?, 0x36?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054580 sp=0x14000054560 pc=0x10008e0a4 runtime.runfinq() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:193 +0x10c fp=0x140000547d0 sp=0x14000054580 pc=0x10006e92c runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000547d0 sp=0x140000547d0 pc=0x1000be234 created by runtime.createfing /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:163 +0x84 goroutine 18 [GC worker (idle) ]: runtime.gopark(0x3ef46395813?, 0x3?, 0x8a?, 0xee?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000056f40 sp=0x14000056f20 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000056fd0 sp=0x14000056f40 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000056fd0 sp=0x14000056fd0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 9 [GC worker (idle)]: runtime.gopark(0x3ebaad96151 ?, 0x3?, 0xbf?, 0xdb?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000057740 sp=0x14000057720 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000577d0 sp=0x14000057740 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000577d0 sp=0x140000577d0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 19 [GC worker (idle)]: runtime.gopark(0x3ef3fe69e5c?, 0x1?, 0xa1?, 0xfa?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go :381 +0xe4 fp=0x14000050740 sp=0x14000050720 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000507d0 sp=0x14000050740 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000507d0 sp=0x140000507d0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 20 [GC worker (idle)]: runtime.gopark(0x3ef463d05cf?, 0x3?, 0x9b?, 0x90?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000050f40 sp=0x14000050f20 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000050fd0 sp=0x14000050f40 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000050fd0 sp=0x14000050fd0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 34 [GC worker (idle)]: runtime.gopark(0x3ef463b14bd?, 0x1?, 0xb1?, 0x96?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000094740 sp=0x14000094720 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000947d0 sp=0x14000094740 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000947d0 sp=0x140000947d0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 35 [GC worker (idle)]: runtime.gopark(0x3ef0e621f41?, 0x3?, 0x2e?, 0x17?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000094f40 sp=0x14000094f20 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000094fd0 sp=0x14000094f40 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000094fd0 sp=0x14000094fd0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 10 [GC worker (idle)]: runtime.gopark(0x3ef0e6222ac?, 0x3?, 0x95?, 0xfe?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000057f40 sp=0x14000057f20 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x14000057fd0 sp=0x14000057f40 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000057fd0 sp=0x14000057fd0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 36 [GC worker (idle)]: runtime.gopark(0x3ef4650b3bb?, 0x1?, 0xf8?, 0xa5? , 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000095740 sp=0x14000095720 pc=0x10008e0a4 runtime.gcBgMarkWorker() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1275 +0xec fp=0x140000957d0 sp=0x14000095740 pc=0x1000717dc runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000957d0 sp=0x140000957d0 pc=0x1000be234 created by runtime.gcBgMarkStartWorkers /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:1199 +0x28 goroutine 1108 [IO wait]: runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x1000d0b90?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000052d40 sp=0x14000052d20 pc=0x10008e0a4 runtime.netpollblock(0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x14000052d80 sp=0x14000052d40 pc=0x1000875c8 internal/poll.runtime_pollWait(0x1282b9838, 0x72) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x14000052db0 sp=0x14000052d80 pc=0x1000b7e00 internal/poll.(*pollDesc).wait(0x14000448000?, 0x140001b23a1?, 0x0) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000052de0 sp=0x14000052db0 pc=0x10013d5f8 internal/poll.(*pollDesc).waitRead(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x14000448000, {0x140001b23a1, 0x1, 0x1}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go :167 +0x200 fp=0x14000052e80 sp=0x14000052de0 pc=0x10013e960 net.(*netFD).Read(0x14000448000, {0x140001b23a1?, 0x14000052f90?, 0x14000120be0?}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_posix.go:55 +0x28 fp=0x14000052ed0 sp=0x14000052e80 pc=0x10017faa8 net.(*conn).Read(0x14000518020, {0x140001b23a1?, 0x0?, 0x0?}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/net.go:183 +0x34 fp=0x14000052f20 sp=0x14000052ed0 pc=0x10018e0b4 net.(*TCPConn).Read( 0x0?, {0x140001b23a1?, 0x0?, 0x1005696a0?}) <autogenerated>:1 +0x2c fp=0x14000052f50 sp=0x14000052f20 pc=0x1001a05fc net/http.(*connReader).backgroundRead(0x140001b2390) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:674 +0x44 fp=0x14000052fb0 sp=0x14000052f50 pc=0x1002cea04 net/http.(*connReader).startBackgroundRead.func2() /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0x28 fp=0x14000052fd0 sp=0x14000052fb0 pc=0x1002ce928 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000052fd0 sp=0x14000052fd0 pc=0x1000be234 created by net/http.(*connReader).startBackgroundRead /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0xcc r0 0x0 r1 0x0 r2 0x0 r3 0x0 r4 0x1aa4d0647 r5 0x16fd91d90 r6 0x6e r7 0x200 r8 0x5cdc9440437c471f r9 0x5cdc94424625279f r10 0x200 r11 0xb r12 0xb r13 0x0 r14 0x0 r15 0x0 r16 0x148 r17 0x20a0bb3a0 r18 0x0 r19 0x6 r20 0x205596080 r21 0x103 r22 0x205596160 r23 0x15379cde0 r24 0x1 r25 0x1508c40a0 r26 0x1 r27 0x20 r28 0x16fdab0f8 r29 0x16fd91d00 lr 0x1aa513c28 sp 0x16fd91ce0 pc 0x1aa4dc764 fault 0x1aa4dc764 [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached. [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production. - using env: export GIN_MODE=release - using code: gin.SetMode(gin.ReleaseMode) [GIN-debug] GET / --> github.com/jmorganca/ollama/server.Serve.func1 (4 handlers) [GIN-debug] POST /api/pull --> github.com/jmorganca/ollama/server.PullModelHandler (4 handlers) [GIN-debug] POST /api/generate --> github.com/jmorganca/ollama/server.GenerateHandler (4 handlers) [GIN-debug] POST /api/create --> github.com/jmorganca/ollama/server.CreateModelHandler (4 handlers) [GIN-debug] POST /api/push --> github.com/jmorganca/ollama/server.PushModelHandler (4 handlers) [GIN-debug] POST /api/copy --> github.com/jmorganca/ollama/server.CopyModelHandler (4 handlers) [GIN-debug] GET /api/tags --> github.com/jmorganca/ollama/server.ListModelsHandler (4 handlers) [GIN-debug] DELETE /api/delete --> github.com/jmorganca/ollama/server.DeleteModelHandler (4 handlers) 2023/08/03 01:24:14 routes.go:276: Listening on 127.0.0.1:11434 ```
GiteaMirror added the bug label 2026-04-12 09:39:01 -05:00
Author
Owner

@BruceMacD commented on GitHub (Aug 3, 2023):

Thanks for reporting this, I was able to reproduce. Looking into it.

<!-- gh-comment-id:1664277558 --> @BruceMacD commented on GitHub (Aug 3, 2023): Thanks for reporting this, I was able to reproduce. Looking into it.
Author
Owner

@drhino commented on GitHub (Aug 3, 2023):

did you use 0.0.12 or 0.0.13? Because maybe..., just maybe, the issue is resolved now that the model is kept into ram. I still have to test that out

<!-- gh-comment-id:1664392106 --> @drhino commented on GitHub (Aug 3, 2023): did you use 0.0.12 or 0.0.13? Because maybe..., just maybe, the issue is resolved now that the model is kept into ram. I still have to test that out
Author
Owner

@BruceMacD commented on GitHub (Aug 3, 2023):

It was on 0.0.13 I reproduced sadly

<!-- gh-comment-id:1664691570 --> @BruceMacD commented on GitHub (Aug 3, 2023): It was on `0.0.13` I reproduced sadly
Author
Owner

@mxyng commented on GitHub (Aug 5, 2023):

I've tested this on the v0.0.13 release using llama2 without any issues, at least nothing catastrophic like a segfault

<!-- gh-comment-id:1666296864 --> @mxyng commented on GitHub (Aug 5, 2023): I've tested this on the v0.0.13 release using llama2 without any issues, at least nothing catastrophic like a segfault
Author
Owner

@drhino commented on GitHub (Aug 5, 2023):

i'll do some further testing and see if i can make a use case thats more easy to reproduce

<!-- gh-comment-id:1666365391 --> @drhino commented on GitHub (Aug 5, 2023): i'll do some further testing and see if i can make a use case thats more easy to reproduce
Author
Owner

@BruceMacD commented on GitHub (Aug 8, 2023):

Confirmed with Mike's update that this doesn't seem to be reproducible after the latest updates. Closing this for now pending any more reports.

<!-- gh-comment-id:1670162145 --> @BruceMacD commented on GitHub (Aug 8, 2023): Confirmed with Mike's update that this doesn't seem to be reproducible after the latest updates. Closing this for now pending any more reports.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#113