llama.cpp/tools
hanishkvc e52a7aa304 SimpleSallap:SimpleProxy: MultiThreading
Given that default HTTPServer handles only one connection and inturn
request at any given time, so if a client opens connection and then
doesnt do anything with it, it will block other clients by putting their
requests into network queue for long.

So to overcome the above issue switch to ThreadingHTTPServer, which
starts a new thread for each request.

Given that previously ssl wrapping was done wrt the main server socket,
even with switching to ThreadingHTTPServer, the handshake for ssl/tls
still occurs in the main thread before a child thread is started for
parallel request handling, thus the ssl handshake phase blocking other
client requests.

So now avoid wrapping ssl wrt the main server socket, instead wait for
ThreadingHttpServer to start the new thread for a client request ie
after a connection is accepted for the client, before trying to wrap
the connection in ssl. This ensures that the ssl handshake occurs in
this child (ie client request related) thread. So some rogue entity
opening a http connection and not doing ssl handshake wont block.

Inturn in this case the rfile and wfile instances within the proxy
handler need to be remapped to the new ssl wrapped socket.
2025-12-05 01:53:12 +05:30
..
batched-bench batched-bench : add "separate text gen" mode (#17103) 2025-11-10 12:59:29 +02:00
cvector-generator cmake : Do not install tools on iOS targets (#15903) 2025-09-16 09:54:44 +07:00
export-lora cmake : Do not install tools on iOS targets (#15903) 2025-09-16 09:54:44 +07:00
gguf-split ci : use smaller model (#16168) 2025-09-22 09:11:39 +03:00
imatrix Manually link -lbsd to resolve flock symbol on AIX (#16610) 2025-10-23 19:37:31 +08:00
llama-bench bench : cache the llama_context state at computed depth (#16944) 2025-11-07 21:23:11 +02:00
main cli: add migration warning (#17620) 2025-11-30 15:32:43 +01:00
mtmd mtmd: fix --no-warmup (#17695) 2025-12-02 22:48:08 +01:00
perplexity perplexity : show more kl-divergence data (#16321) 2025-09-29 09:30:45 +03:00
quantize ci : use smaller model (#16168) 2025-09-22 09:11:39 +03:00
rpc Install rpc-server when GGML_RPC is ON. (#17149) 2025-11-11 10:53:59 +00:00
run Manually link -lbsd to resolve flock symbol on AIX (#16610) 2025-10-23 19:37:31 +08:00
server SimpleSallap:SimpleProxy: MultiThreading 2025-12-05 01:53:12 +05:30
tokenize cmake : Do not install tools on iOS targets (#15903) 2025-09-16 09:54:44 +07:00
tts model : Apertus model implementation (#15852) 2025-10-02 20:43:22 +03:00
CMakeLists.txt mtmd : rename llava directory to mtmd (#13311) 2025-05-05 16:02:55 +02:00