Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
v4: max_tokens is a ceiling — clamp to context instead of rejecting (#975)
JustVugg8c40fbddc74d
diff --git a/c/coli b/c/coliindex 8d968f45..1e0127d6 100755--- a/c/coli+++ b/c/coli@@ -1003,7 +1003,7 @@ def chat_attached(a, base, model_id):its KV slots reuse the conversation prefix, so a continued chat skipsre-prefill too. The engine byte-protocol stays untouched — this is plainOpenAI SSE over localhost, stdlib only."""- import urllib.request+ import urllib.request, urllib.errorprint(f" {C.grn}✦ attached{C.r} {C.dim}to {base} · model {model_id} · the engine stays warm after you quit{C.r}")print(f" {C.dim}type and press Enter · Ctrl-C stops the answer · :reset starts a new conversation · :q exits{C.r}\n")msgs=[]@@ -1048,6 +1048,20 @@ def chat_attached(a, base, model_id):md.feed(txt); reply.append(txt)except KeyboardInterrupt:interrupted=True # il server annulla la richiesta alla disconnessione+ except urllib.error.HTTPError as e:+ # HTTPError IS-A OSError: without this arm a 4xx/5xx fell into the+ # branch below and read as "server unreachable" — hiding the API's+ # own explanation of what was wrong with the request (#975: a V4+ # CONTEXT_EXCEEDED 400 took a screenshot to diagnose instead of a+ # sentence). The body is OpenAI-shaped; show its message.+ sp.stop()+ try:+ detail=json.loads(e.read().decode("utf-8","replace")).get("error",{}).get("message","")+ except Exception:+ detail=""+ print(f"\n {C.yel}[the server rejected the request: HTTP {e.code}"+ f"{' — '+detail if detail else ''}]{C.r}")+ msgs.pop(); continue # la richiesta non è mai partita: togli il turno e riprovaexcept OSError as e:sp.stop()print(f"\n {C.yel}[server unreachable: {e}]{C.r}"); breakdiff --git a/c/deepseek_v4.c b/c/deepseek_v4.cindex fe94d5c3..d2bd6d5f 100644--- a/c/deepseek_v4.c+++ b/c/deepseek_v4.c@@ -8742,7 +8742,9 @@ static void v4_serve_one(ColiV4Engine *engine, ColiV4Session *session,session->max_prompt_tokens + 16);int context = engine->runtime.context_tokens;if (prompt_count < 1 || prompt_count > session->max_prompt_tokens ||- prompt_count + request->max_tokens > context) {+ prompt_count + 1 > context) {+ /* The PROMPT does not fit (or leaves no room for a single generated+ * token) -- that is the only honest CONTEXT_EXCEEDED. */char message[256];snprintf(message, sizeof(message),"CONTEXT_EXCEEDED prompt_tokens=%d requested=%d capacity=%d",@@ -8750,6 +8752,19 @@ static void v4_serve_one(ColiV4Engine *engine, ColiV4Session *session,v4_serve_error(request->id, message);return;}+ /* max_tokens is a CEILING, not a target (#260/#382): generation ends at+ * EOS either way, so an oversized budget is clamped to what the context+ * can hold -- the same semantics the GLM serve path has had since #260.+ * Rejecting instead made `coli chat`'s interactive default (16384) a+ * guaranteed 400 on every first message of a fresh V4 chat (#975). */+ if (request->max_tokens > context - prompt_count) {+ fprintf(stderr,+ "[V4] max_tokens %d clamped to %d (context %d - prompt %d); "+ "raise CTX for longer answers\n",+ request->max_tokens, context - prompt_count, context,+ prompt_count);+ request->max_tokens = context - prompt_count;+ }printf("ACCEPT %s %d\n", request->id, prompt_count);fflush(stdout);diff --git a/docs/deepseek-v4.md b/docs/deepseek-v4.mdindex 415f610f..bc1251b8 100644--- a/docs/deepseek-v4.md+++ b/docs/deepseek-v4.md@@ -71,6 +71,10 @@ python ./coli serve --model /path/to/DeepSeek-V4-Flash --ram 32python ./coli web --model /path/to/DeepSeek-V4-Flash --ram 32```+Generation length: `--ngen` is a ceiling, not a target — answers end at EOS.+If the ceiling exceeds what the context window can hold, the engine clamps it+and says so on stderr; raise `CTX` for genuinely longer answers.+V4 chat uses native model markers. Native serving currently supports greedygeneration and one active KV slot; tools and grammar are rejected. Requestsre-prefill their context, while the process, weights, dense tensors, head, and